© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130398
    Prev
    Next
    INDEX
    Explanations

    are visible

    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_6_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
    то
    1.02
    TimeStamp
    0.99
    ן
    0.93
    కు
    0.92
     ampliamente
    0.92
     locais
    0.89
    ด
    0.85
    很
    0.84
    ცა
    0.83
     بسي
    0.83
    POSITIVE LOGITS
    0.89
    ral
    0.87
    v
    0.85
     It
    0.84
    ries
    0.84
    ni
    0.84
    </
    0.83
    ")]
    0.83
    </h2>
    0.82
    h
    0.80
    Activations Density 0.022%

    No Known Activations