© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 51179
    Prev
    Next
    INDEX
    Explanations

    being responsible

    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_55_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
     old
    0.55
     cũ
    0.41
    낡
    0.40
    旧
    0.39
     fitted
    0.38
     alten
    0.38
     حرف
    0.38
    सिस
    0.37
    舊
    0.37
    ऱ्यावर
    0.37
    POSITIVE LOGITS
    cie
    0.38
    ustellen
    0.38
    dle
    0.37
     phospho
    0.36
    presas
    0.36
     gage
    0.36
    üd
    0.36
    プレス
    0.35
     vang
    0.35
    acci
    0.35
    Activations Density 0.030%

    No Known Activations