© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7770
    Prev
    Next
    INDEX
    Explanations

    fragments of text taken from lists or semi-structured text

    oai_token-act-pair · gemini-2.0-flash

    /

    np_max-act-logits · gemini-2.0-flash

    /

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    ResumeLayout
    -0.61
    PhysRev
    -0.59
    DllImport
    -0.53
    argout
    -0.52
     mapStateToProps
    -0.51
    ________,
    -0.51
     AssemblyVersion
    -0.50
    WebElementEntity
    -0.50
    AutoScale
    -0.49
     XNUMX
    -0.49
    POSITIVE LOGITS
     new
    0.68
     own
    0.67
     right
    0.63
     current
    0.63
     small
    0.63
     work
    0.63
     other
    0.63
     existing
    0.63
     whole
    0.63
     next
    0.62
    Activations Density 18.493%

    No Known Activations