© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79399
    Prev
    Next
    INDEX
    Explanations

    math statements

    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_0_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
     for
    1.63
    ה
    1.45
     is
    1.28
    া
    1.26
    ه
    1.16
    ))
    1.14
     ו
    1.13
     not
    1.10
    1.06
     be
    1.03
    POSITIVE LOGITS
    to
    2.06
    y
    1.95
    n
    1.77
    ta
    1.64
    ra
    1.58
    the
    1.55
    ts
    1.52
    m
    1.45
    ten
    1.42
    ش
    1.41
    Activations Density 0.000%

    No Known Activations