© 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. 89660
    Prev
    Next
    INDEX
    Explanations

    regnal years, Reggie White, RegNet, Regina Spektor

    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
    is
    1.21
    ut
    0.89
    ু
    0.85
    ی
    0.76
    л
    0.75
    ي
    0.72
    am
    0.70
    س
    0.70
     regolare
    0.69
     RegExp
    0.68
    POSITIVE LOGITS
    t
    0.89
     católica
    0.64
    ποιή
    0.59
    tke
    0.59
    tor
    0.59
    }$).
    0.59
    lø
    0.58
    nö
    0.58
    rmse
    0.57
    larghezza
    0.57
    Activations Density 0.000%

    No Known Activations