© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 237469
    Prev
    Next
    INDEX
    Explanations

    replacements and new members

    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_25_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
     catfish
    0.29
     новые
    0.28
     cate
    0.28
     추가
    0.28
     Introduce
    0.28
    钾
    0.28
     purposeful
    0.27
     tambahan
    0.27
     φ
    0.27
    għ
    0.27
    POSITIVE LOGITS
    stops
    0.29
    tiers
    0.28
    village
    0.26
    painted
    0.26
    steps
    0.26
    physics
    0.25
    司法
    0.25
    mailer
    0.25
    citing
    0.25
     Mut
    0.25
    Activations Density 0.000%

    No Known Activations