© 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. 123076
    Prev
    Next
    INDEX
    Explanations

    worth considering or estimating value

    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
    h
    1.01
    ]^
    0.77
    تی
    0.75
    ti
    0.75
    nytimes
    0.74
    q
    0.74
    hk
    0.74
    j
    0.74
    ществует
    0.73
    f
    0.73
    POSITIVE LOGITS
     غير
    0.81
     entdecken
    0.78
     سي
    0.77
    كه
    0.71
     كانت
    0.70
    زيد
    0.70
    ar
    0.68
     قي
    0.68
     sicht
    0.68
     reicht
    0.68
    Activations Density 0.000%

    No Known Activations