© 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. 7999
    Prev
    Next
    INDEX
    Explanations

    words related to crime, persuasion, creation and slavery

    oai_token-act-pair · gemini-2.0-flash

    say "er" ending

    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
    Rhestr
    -0.61
     Besuch
    -0.50
    httphttps
    -0.47
    例文
    -0.47
     Villanueva
    -0.46
    HOLD
    -0.46
     Paix
    -0.45
    Discografia
    -0.45
     Hj
    -0.45
    CopyWith
    -0.45
    POSITIVE LOGITS
    ner
    0.96
    NER
    0.92
    ber
    0.89
    mer
    0.87
    acer
    0.84
    aner
    0.84
    INER
    0.84
    ter
    0.83
    iter
    0.83
    cter
    0.83
    Activations Density 10.064%

    No Known Activations