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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15055
    Prev
    Next
    INDEX
    Explanations

    statements that evaluate the usefulness, impact or relevance of something

    oai_token-act-pair · gemini-2.0-flash

    PhysRev

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    tanleria
    -0.58
    راسیون
    -0.55
     TextInput
    -0.54
    GOTREF
    -0.54
    VersionUID
    -0.54
    وط
    -0.53
    dersfield
    -0.52
     eus
    -0.51
     Himo
    -0.50
     XNUMX
    -0.50
    POSITIVE LOGITS
    PhysRev
    0.55
    izmu
    0.51
    BufferException
    0.51
     intptr
    0.51
    Vegeu
    0.50
    ++]=
    0.49
     rallado
    0.48
    $_['
    0.48
     Leeuwen
    0.48
     sanitaires
    0.46
    Activations Density 11.470%

    No Known Activations