© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 105745
    Prev
    Next
    INDEX
    Explanations

    George followed by names or actions

    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_1_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
     on
    1.63
     as
    1.38
    0
    1.32
    1
    1.22
     are
    1.20
    ",
    1.17
     of
    1.16
    ;
    1.15
     a
    1.09
    2
    1.05
    POSITIVE LOGITS
    ي
    1.76
    z
    1.52
    j
    1.34
    ர்
    1.32
    an
    1.27
    i
    1.27
    ر
    1.27
    will
    1.19
    يان
    1.19
    uk
    1.16
    Activations Density 0.000%

    No Known Activations