© 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-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 167577
    Prev
    Next
    INDEX
    Explanations

    collection

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     StandardScaler
    0.40
    slime
    0.38
     reservoirs
    0.36
    パク
    0.36
    ERSHIP
    0.36
    㤈
    0.35
    hua
    0.35
    instag
    0.34
    ડો
    0.34
     हेल्
    0.34
    POSITIVE LOGITS
     collection
    2.06
     Collection
    2.03
    Collection
    1.91
    collection
    1.88
     COLLECTION
    1.73
     colección
    1.45
     collezione
    1.33
     coleção
    1.33
     कलेक्शन
    1.30
    藏
    1.30
    Activations Density 0.001%

    No Known Activations