© 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-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 46049
    Prev
    Next
    INDEX
    Explanations

    dark web links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_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
    s
    0.82
    }
    0.77
    )
    0.69
     was
    0.68
    การ
    0.68
    \
    0.66
     but
    0.66
     architectural
    0.66
     from
    0.65
    </h2>
    0.64
    POSITIVE LOGITS
    ТА
    0.66
     وغيرها
    0.66
    SK
    0.64
    nym
    0.64
    Все
    0.64
    蒉
    0.62
    মাম
    0.61
    嚧
    0.61
    ፁ
    0.60
    SN
    0.59
    Activations Density 0.003%

    No Known Activations