© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 31935
    Prev
    Next
    INDEX
    Explanations

    identifiers/codes

    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_50_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
    près
    0.41
    IVE
    0.39
    PAUL
    0.38
    печа
    0.38
    sal
    0.38
     ी
    0.36
    OCATION
    0.36
     PAUL
    0.36
    cay
    0.35
     Schulz
    0.35
    POSITIVE LOGITS
    ers
    0.44
    దీ
    0.43
    erais
    0.39
    木
    0.38
     అన
    0.38
    rui
    0.38
     dictators
    0.37
    ERS
    0.37
    稀
    0.36
    Async
    0.35
    Activations Density 0.023%

    No Known Activations