© 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. 144274
    Prev
    Next
    INDEX
    Explanations

    FV or fv

    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
    ι
    1.41
    ین
    1.30
    ために
    1.30
    ва
    1.24
    uje
    1.23
    েন
    1.23
    ینگ
    1.20
    น
    1.16
    ě
    1.16
    ือ
    1.15
    POSITIVE LOGITS
    d
    1.97
    c
    1.86
    w
    1.84
    g
    1.69
    s
    1.63
    the
    1.57
    in
    1.51
    a
    1.46
    r
    1.45
    k
    1.41
    Activations Density 0.001%

    No Known Activations