© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 127216
    Prev
    Next
    INDEX
    Explanations

    Bearer token authentication

    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_37_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
     паспо
    0.40
    𝗬
    0.40
     প্রয
    0.38
     Mercury
    0.37
     Refuge
    0.37
    apellido
    0.37
    నించ
    0.36
    >();
    0.35
     Pu
    0.35
    Lav
    0.35
    POSITIVE LOGITS
     カーボン
    0.38
    othesis
    0.38
    ards
    0.36
     قوم
    0.35
     guerrilla
    0.35
     उदासीन
    0.35
    ard
    0.34
     Entries
    0.34
    BuildActionEntry
    0.34
    Entries
    0.34
    Activations Density 0.001%

    No Known Activations