© 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. 2117
    Prev
    Next
    INDEX
    Explanations

    words or phrases used to give an evaluation.

    oai_token-act-pair · gemini-2.0-flash

    terms related to images and metadata

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

    Images

    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
     يتيمه
    -0.79
    AndEndTag
    -0.77
     CommonModule
    -0.61
    >{@
    -0.59
     SDLK
    -0.58
    ніципа
    -0.58
    enumii
    -0.58
    lipas
    -0.58
    AutoScaleMode
    -0.56
    fromnode
    -0.56
    POSITIVE LOGITS
    meta
    0.71
     images
    0.71
     meta
    0.66
     image
    0.65
     Meta
    0.64
    Meta
    0.64
     picture
    0.62
    img
    0.61
    images
    0.60
     imagery
    0.60
    Activations Density 2.916%

    No Known Activations