© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 93680
    Prev
    Next
    INDEX
    Explanations

    say "det" or "dist" suffixes

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
    OLD
    0.46
    ractions
    0.42
     hoá
    0.41
    aud
    0.40
    hale
    0.40
    ര്‍
    0.40
    rag
    0.40
    r
    0.40
    rad
    0.39
    houd
    0.39
    POSITIVE LOGITS
    ail
    0.55
    ondan
    0.46
     Creating
    0.44
    寤
    0.41
    Creating
    0.40
    entz
    0.40
    ന്ത്യ
    0.39
    বৃন্দ
    0.39
     Entities
    0.38
    𝘬
    0.38
    Activations Density 0.000%

    No Known Activations