© 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. 232691
    Prev
    Next
    INDEX
    Explanations

    transactions

    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
    et
    1.57
    j
    1.55
    or
    1.47
    ol
    1.43
    ai
    1.43
    ur
    1.42
    z
    1.35
    y
    1.28
    ir
    1.26
    av
    1.25
    POSITIVE LOGITS
    你
    0.86
    他的
    0.85
     setIs
    0.85
    جة
    0.84
    ใจ
    0.84
     pogod
    0.82
    If
    0.80
     baseY
    0.79
    以
    0.79
    一个
    0.79
    Activations Density 0.000%

    No Known Activations