© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33623
    Prev
    Next
    INDEX
    Explanations

    hacksaw, based, lang, food, buffer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_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
    ne
    0.68
    1
    0.62
     de
    0.61
    5
    0.60
    illy
    0.58
    ziel
    0.56
    ]
    0.56
    ively
    0.55
    lee
    0.55
    chel
    0.55
    POSITIVE LOGITS
    ك
    0.95
    る
    0.92
    ק
    0.87
    ר
    0.77
    𝘢
    0.77
    고
    0.74
    ﻛ
    0.74
    اک
    0.68
    क
    0.68
    ಿಯಾ
    0.66
    Activations Density 0.019%

    No Known Activations