© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7466
    Prev
    Next
    INDEX
    Explanations

    legal and financial agreements

    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_40_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
     অনুরোধ
    0.38
     consolation
    0.38
     봉
    0.37
     Towa
    0.37
     request
    0.37
    elter
    0.35
     Tú
    0.35
    েন্টে
    0.35
    Council
    0.35
    genza
    0.35
    POSITIVE LOGITS
    ___
    0.36
    iliy
    0.36
    __
    0.35
     &_
    0.35
     PER
    0.35
    Dockerfile
    0.34
    standalone
    0.34
     Morty
    0.33
    Volume
    0.32
    꺽
    0.32
    Activations Density 0.019%

    No Known Activations