© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42380
    Prev
    Next
    INDEX
    Explanations

    by describing/touching/looking/going/observing

    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_3_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
     IGP
    0.76
    m
    0.71
    x
    0.71
    il
    0.68
     IVF
    0.68
     WWF
    0.68
     DPRD
    0.67
    க
    0.66
    פ
    0.66
     AAU
    0.66
    POSITIVE LOGITS
    5
    0.84
    1
    0.72
    ва
    0.70
    4
    0.70
    NE
    0.66
    3
    0.66
    з
    0.66
     .
    0.65
    elling
    0.63
    SON
    0.62
    Activations Density 0.006%

    No Known Activations