© 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. 6748
    Prev
    Next
    INDEX
    Explanations

    citations of legal documents

    oai_token-act-pair · gemini-2.0-flash

    Random character strings

    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
     joaat
    -0.38
    UnknownFields
    -0.38
     burberry
    -0.38
    cault
    -0.36
    Propel
    -0.36
    Referencer
    -0.35
     للمعارف
    -0.35
    ῖν
    -0.33
    يكب
    -0.33
    نح
    -0.32
    POSITIVE LOGITS
    S
    0.76
    SG
    0.66
    s
    0.66
    SV
    0.63
    исленность
    0.63
     estekak
    0.62
    Sg
    0.61
    $
    0.60
    }$\
    0.60
    !’
    0.59
    Activations Density 38.549%

    No Known Activations