© 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. 80577
    Prev
    Next
    INDEX
    Explanations

    bewildering

    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
    к
    1.35
    ק
    1.27
    ார்
    1.23
    .`
    1.23
    .
    1.22
    .}}
    1.21
    .").
    1.20
    аз
    1.20
    н
    1.18
     maestros
    1.16
    POSITIVE LOGITS
    l
    2.16
    g
    2.16
    d
    2.08
    t
    1.98
    s
    1.98
    r
    1.81
    は
    1.77
    는
    1.72
    ll
    1.63
    c
    1.59
    Activations Density 0.000%

    No Known Activations