© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5954
    Prev
    Next
    INDEX
    Explanations

    words related to technological specifications and academic research

    oai_token-act-pair · gemini-2.0-flash

    capabilities and possibilities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    AndEndTag
    -0.68
     الحره
    -0.59
    awaiter
    -0.58
     policiales
    -0.57
    PullParser
    -0.55
    DeleteBehavior
    -0.55
    setVerticalGroup
    -0.55
     étrang
    -0.54
     betweenstory
    -0.54
     démo
    -0.53
    POSITIVE LOGITS
     realizing
    0.47
     Play
    0.47
    +#+#
    0.47
    pidou
    0.46
     avoids
    0.45
    play
    0.44
     realizes
    0.44
     realize
    0.44
    Play
    0.44
     Ow
    0.43
    Activations Density 3.262%

    No Known Activations