© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8321
    Prev
    Next
    INDEX
    Explanations

    patterns of conversational text and lists

    oai_token-act-pair · gemini-2.0-flash

    offer

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    __);
    -0.68
    ]]);
    -0.65
     ब्रेकडाउन
    -0.60
     pinulongan
    -0.60
    ]--;
    -0.59
    "]);
    -0.58
    "])
    -0.56
    eramente
    -0.55
     Plenum
    -0.55
    "]).
    -0.54
    POSITIVE LOGITS
     offer
    2.14
    Offer
    1.94
     offering
    1.91
     Offer
    1.91
    offer
    1.87
     OFFER
    1.82
     offered
    1.80
     offers
    1.80
     Offering
    1.72
    Offering
    1.68
    Activations Density 6.508%

    No Known Activations