© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 34122
    Prev
    Next
    INDEX
    Explanations

    Mystic Adept or friend

    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
    h
    1.54
    al
    1.37
    i
    1.34
    2
    1.34
    l
    1.32
    f
    1.32
    1
    1.31
    t
    1.30
    u
    1.29
    den
    1.28
    POSITIVE LOGITS
     for
    1.41
     be
    1.13
    な
    1.09
    한
    1.05
    ので
    1.05
     about
    1.01
    ING
    0.98
     поможет
    0.98
     prend
    0.96
     deepen
    0.95
    Activations Density 0.000%

    No Known Activations