© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 27505
    Prev
    Next
    INDEX
    Explanations

    Subject: Re:

    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
    ()"
    0.40
     الإسلام
    0.38
     cocon
    0.38
     м
    0.38
     percepción
    0.38
    ޟ
    0.36
     perceived
    0.36
    AssetDiscovery
    0.36
     ম
    0.35
     %),
    0.35
    POSITIVE LOGITS
    books
    0.44
    book
    0.44
    immediately
    0.43
     IMMEDI
    0.43
    Team
    0.43
     গ্রন্থ
    0.42
    jami
    0.41
    வந்த
    0.40
    Personnel
    0.40
     immediately
    0.39
    Activations Density 0.002%

    No Known Activations