© 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. 6964
    Prev
    Next
    INDEX
    Explanations

    song titles

    oai_token-act-pair · gemini-2.0-flash

    song titles/lyrics

    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
    FlatAppearance
    -0.51
     saites
    -0.49
    uParam
    -0.46
     assets
    -0.45
    ServletException
    -0.44
    PyExc
    -0.44
    Pyx
    -0.43
    ruct
    -0.43
     Fenn
    -0.43
    DllImport
    -0.42
    POSITIVE LOGITS
     autorytatywna
    0.71
    SourceChecksum
    0.68
    存于互联网档案馆
    0.63
    Lonely
    0.60
     Hear
    0.59
     Kiss
    0.59
    Gotta
    0.59
     Gotta
    0.58
     Lonely
    0.57
     Lover
    0.54
    Activations Density 5.661%

    No Known Activations