© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 30786
    Prev
    Next
    INDEX
    Explanations

    know about

    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_7_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
    at
    0.60
    an
    0.58
    u
    0.55
    as
    0.50
    و
    0.47
    ו
    0.45
    a
    0.44
    our
    0.43
    w
    0.43
    ุ
    0.43
    POSITIVE LOGITS
     revolve
    0.36
     impede
    0.35
     clarify
    0.34
     encourage
    0.33
     are
    0.32
    ）,
    0.32
     accommodate
    0.31
    HNO
    0.31
    槌
    0.31
     observe
    0.31
    Activations Density 0.004%

    No Known Activations