Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 33-GEMMASCOPE-2-TRANSCODER-262K
    4. 261357
    Prev
    Next
    INDEX
    Explanations

    immortal jellyfish

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_33_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
     зон
    0.69
    )%>%
    0.66
     geo
    0.65
     tepung
    0.64
     handset
    0.64
    ємо
    0.62
    abei
    0.62
     noodle
    0.61
    潞
    0.60
    ภาพ
    0.60
    POSITIVE LOGITS
    Michigan
    0.87
    think
    0.82
    CLA
    0.80
    cv
    0.79
     SPMs
    0.79
    DbContext
    0.77
    Spar
    0.76
    GU
    0.74
    contr
    0.73
    comprom
    0.73
    Activations Density 0.001%

    No Known Activations