© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 219861
    Prev
    Next
    INDEX
    Explanations

    return f"

    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_31_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
    INSON
    0.20
    醋
    0.20
    ני
    0.19
    WEEN
    0.19
    SOLE
    0.19
     mentored
    0.19
    Ink
    0.19
    <s>
    0.18
    뎀
    0.18
    endment
    0.18
    POSITIVE LOGITS
     নেট
    0.22
     ಹೆಚ್ಚಿನ
    0.22
     названием
    0.22
     Stealth
    0.22
     Encounter
    0.21
     వార్
    0.21
     elektronic
    0.21
     décidé
    0.21
     elb
    0.21
    資訊
    0.20
    Activations Density 0.000%

    No Known Activations