© 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. 130519
    Prev
    Next
    INDEX
    Explanations

    ColossalClean

    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
    ж
    0.98
    де
    0.90
    ма
    0.89
    િંગ
    0.89
    രീ
    0.88
    ю
    0.87
    ру
    0.85
    их
    0.85
    ىن
    0.84
    ור
    0.84
    POSITIVE LOGITS
    .
    0.88
    2
    0.88
    ad
    0.83
    ↵
    0.80
    et
    0.80
    什么样的
    0.79
     bastion
    0.78
    >
    0.77
     Creativity
    0.76
    ledning
    0.76
    Activations Density 0.000%

    No Known Activations