© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20344
    Prev
    Next
    INDEX
    Explanations

    code repositories

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    hk
    0.37
     Hk
    0.36
     £
    0.35
     formalities
    0.35
    اة
    0.35
    £
    0.35
    ູ້
    0.35
    ,))
    0.35
     બનાવવા
    0.35
     gb
    0.34
    POSITIVE LOGITS
     repos
    0.44
     Ap
    0.39
    Repo
    0.39
     Repo
    0.38
    áp
    0.37
    ">−</
    0.37
    )^{\
    0.37
    repos
    0.37
     repository
    0.36
     UserRepository
    0.36
    Activations Density 0.002%

    No Known Activations