© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3680
    Prev
    Next
    INDEX
    Explanations

    words related to military weapons and explosions, with a secondary focus on dates

    oai_token-act-pair · gemini-2.0-flash

    explosives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     للاسماء
    -0.65
    fjspx
    -0.63
    chengladbach
    -0.60
    LookAnd
    -0.58
    SequentialGroup
    -0.57
    ]--;
    -0.56
     thermique
    -0.56
     beginnetje
    -0.54
    abetes
    -0.52
     considérons
    -0.52
    POSITIVE LOGITS
    <bos>
    0.58
    GRANTED
    0.49
     Besøkt
    0.49
     Samar
    0.47
    صول
    0.45
    Przypisy
    0.45
    IBar
    0.45
     Witkin
    0.45
    /*
    0.44
    rapie
    0.44
    Activations Density 23.361%

    No Known Activations