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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7783
    Prev
    Next
    INDEX
    Explanations

    software licenses

    oai_token-act-pair · gemini-2.0-flash

    Licenses/Agreements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ChildScrollView
    -1.23
     purpoſe
    -1.22
     cauſe
    -1.18
     ſtate
    -1.18
     ſmall
    -1.13
    AutoScaleMode
    -1.13
     ſtand
    -1.13
    principalColumn
    -1.11
     ainfi
    -1.10
     дописавши
    -1.09
    POSITIVE LOGITS
    For
    0.58
    </i>
    0.56
    H
    0.54
     For
    0.54
    6
    0.54
    1
    0.53
     [
    0.53
    man
    0.52
    /
    0.52
    5
    0.51
    Activations Density 1.497%

    No Known Activations