© 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. 1338
    Prev
    Next
    INDEX
    Explanations

    seemingly random characters, numbers and symbols

    oai_token-act-pair · gemini-2.0-flash

    say "The"

    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
    resaid
    -0.71
    cknow
    -0.70
    StoreMessageInfo
    -0.64
    uxxxx
    -0.61
    AlterField
    -0.61
    OOTDTY
    -0.61
     The
    -0.60
     دریافت‌شده
    -0.60
    Kjelder
    -0.59
    BitConverter
    -0.59
    POSITIVE LOGITS
    The
    1.02
    ÁND
    0.54
     innamor
    0.52
    self
    0.51
     tulang
    0.46
    Abitanti
    0.46
    ecio
    0.46
     AssertionError
    0.44
     croix
    0.44
     indicated
    0.43
    Activations Density 12.640%

    No Known Activations