© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89075
    Prev
    Next
    INDEX
    Explanations

    sticking together

    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_3_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
    و
    0.75
    িন
    0.68
    ’
    0.60
    ahul
    0.58
    attuale
    0.57
     Normandy
    0.56
     jett
    0.55
    𝒐
    0.55
     tony
    0.55
    }\|^{
    0.54
    POSITIVE LOGITS
     footing
    0.69
    ps
    0.63
     expedited
    0.62
    Y
    0.61
    처럼
    0.61
    ts
    0.60
    غ
    0.60
    ig
    0.60
    ทราบ
    0.60
     करते
    0.58
    Activations Density 0.000%

    No Known Activations