© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175612
    Prev
    Next
    INDEX
    Explanations

    CDS Hooks Project Management

    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_20_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
    ༸
    0.45
    诞生
    0.43
     այդ
    0.42
     ಬ್ಯಾ
    0.42
    LLER
    0.41
    hydraulic
    0.40
     ܗ
    0.39
     sự
    0.39
     fator
    0.39
    𝙫
    0.39
    POSITIVE LOGITS
    Plus
    0.46
     Plus
    0.45
     (
    0.41
     Thomas
    0.41
    WithObjects
    0.39
     openly
    0.38
     thomas
    0.38
    PLUS
    0.38
     andre
    0.38
     simplement
    0.38
    Activations Density 0.000%

    No Known Activations