© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6284
    Prev
    Next
    INDEX
    Explanations

    fine-tune on specific tasks/datasets

    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_39_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
    膺
    0.38
     Glück
    0.36
    天氣
    0.36
    !--
    0.35
    Sounds
    0.35
    Portable
    0.34
     Fiore
    0.34
    "]},{"
    0.34
    ="<?=
    0.34
     長
    0.33
    POSITIVE LOGITS
     relevant
    0.47
    relevant
    0.47
     specific
    0.43
     matchups
    0.43
     opposition
    0.43
    pecific
    0.42
    specific
    0.39
    Relevant
    0.38
     driver
    0.38
     Relevant
    0.38
    Activations Density 0.008%

    No Known Activations