© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 104660
    Prev
    Next
    INDEX
    Explanations

    arising

    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
     г
    1.21
     summarise
    1.09
     isotopes
    1.09
     footnote
    1.05
     play
    0.99
     milliliters
    0.99
     telescope
    0.99
     fractions
    0.98
     כך
    0.96
     tangente
    0.96
    POSITIVE LOGITS
    gov
    1.30
    ре
    1.28
    f
    1.21
    <bos>
    1.20
     melaksanakan
    1.20
    j
    1.18
    rell
    1.17
    ｈ
    1.17
    are
    1.16
    lang
    1.15
    Activations Density 0.001%

    No Known Activations