© 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. 1411
    Prev
    Next
    INDEX
    Explanations

    high head, low flow, high speed

    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
     проекта
    0.37
     Convertible
    0.36
     गिर
    0.35
    Ủ
    0.35
     Libyan
    0.35
     Cabrio
    0.35
     poveć
    0.34
    මට
    0.34
    apd
    0.34
     переход
    0.34
    POSITIVE LOGITS
     Bose
    0.35
     চান
    0.34
     সঞ্জ
    0.32
     rel
    0.32
     leta
    0.31
    ormány
    0.31
    წ
    0.31
     Aguilar
    0.31
    रेडी
    0.31
    SIN
    0.31
    Activations Density 0.067%

    No Known Activations