© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9565
    Prev
    Next
    INDEX
    Explanations

    sentences which contain numbers or measurements in a scientific context, often involving comparisons or evaluations

    oai_token-act-pair · gemini-2.0-flash

    words related to reaching or attaining

    np_token-act-pair-logits · gpt-4o-mini

    reach

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedCtor
    -0.63
    fromnode
    -0.61
     arşivlendi
    -0.57
    softc
    -0.56
    ")]
    -0.52
     Roskov
    -0.52
    ỡng
    -0.52
    hoeddwyd
    -0.51
     دیکھیے
    -0.51
     CURIAM
    -0.50
    POSITIVE LOGITS
     reach
    0.61
     reaches
    0.58
    SWG
    0.54
     reaching
    0.54
     reached
    0.53
     Reaching
    0.51
    منابع
    0.50
    :✨
    0.49
    Hochspringen
    0.48
    reaching
    0.47
    Activations Density 1.042%

    No Known Activations