© 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. 8113
    Prev
    Next
    INDEX
    Explanations

    place names and the word "flooding".

    oai_token-act-pair · 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
     kasarigan
    -0.76
     ExecuteAsync
    -0.63
    cyklopedia
    -0.60
    évaluateur
    -0.58
    IVEREF
    -0.52
     gynhyrchwyd
    -0.52
    SharedCtor
    -0.52
    RTSC
    -0.51
     OFDb
    -0.50
     canlynol
    -0.50
    POSITIVE LOGITS
    gående
    0.60
     mourir
    0.55
    rhein
    0.55
     køb
    0.54
     secondaires
    0.54
     bénévoles
    0.54
    ibig
    0.54
     meurt
    0.53
     nemico
    0.52
     Distrito
    0.51
    Activations Density 1.199%

    No Known Activations