© 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. 205218
    Prev
    Next
    INDEX
    Explanations

    foreign characters

    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
    IDS
    0.37
    Comté
    0.37
    ämm
    0.37
    onday
    0.35
    ządz
    0.35
    峋
    0.35
    ESD
    0.34
    识
    0.34
    电压
    0.33
    畦
    0.33
    POSITIVE LOGITS
    ़
    0.90
    ্ব
    0.89
    ্বা
    0.72
    ্বার
    0.71
    ্বের
    0.71
    ht
    0.67
    Ъ
    0.64
    ্বে
    0.62
    ъ
    0.62
    ਼
    0.60
    Activations Density 0.009%

    No Known Activations