© 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. 134329
    Prev
    Next
    INDEX
    Explanations

    cut down

    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
    یس
    0.97
    ב
    0.86
    ی
    0.79
    یت
    0.72
    ید
    0.68
    取り付け
    0.67
    ]।
    0.66
    있
    0.64
    いた
    0.62
    きっと
    0.62
    POSITIVE LOGITS
    m
    0.88
    em
    0.75
     في
    0.74
    ي
    0.74
    et
    0.73
    .
    0.72
    el
    0.67
    i
    0.66
    و
    0.64
    z
    0.64
    Activations Density 0.000%

    No Known Activations