© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81107
    Prev
    Next
    INDEX
    Explanations

    axis labels

    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_0_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
     was
    1.93
    s
    1.87
     can
    1.70
    是
    1.69
    ться
    1.60
    いた
    1.52
     are
    1.51
     is
    1.39
    将
    1.38
    PUT
    1.36
    POSITIVE LOGITS
    ong
    1.55
    л
    1.44
    و
    1.34
    ay
    1.27
    ang
    1.24
    uk
    1.24
    il
    1.20
    ０
    1.18
    ता
    1.16
    와의
    1.14
    Activations Density 0.001%

    No Known Activations