© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 204934
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
     YAP
    0.38
    prar
    0.37
    лях
    0.37
    Ｓ
    0.36
    (''
    0.36
    OffsetY
    0.35
    esterday
    0.34
    덱
    0.34
    턱
    0.34
    ANK
    0.34
    POSITIVE LOGITS
     purposefully
    0.46
     purposely
    0.42
     intentionally
    0.42
     fictional
    0.41
    有效地
    0.41
     அவற்ற
    0.40
    तलब
    0.40
    GetInt
    0.38
    év
    0.38
    }$}
    0.38
    Activations Density 0.001%

    No Known Activations