© 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. 169644
    Prev
    Next
    INDEX
    Explanations

    )

    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
     “
    0.38
     nidd
    0.37
    図柄
    0.37
    IU
    0.37
    ніципа
    0.36
    、“
    0.36
     ਸਿੰ
    0.36
     Fo
    0.35
     ted
    0.35
    phenylsulfanyl
    0.35
    POSITIVE LOGITS
    +'-
    0.46
    '=>
    0.43
    //=
    0.40
    isição
    0.40
    न्व
    0.38
    /');
    0.38
     advanced
    0.38
     assessment
    0.37
    ');//
    0.37
     Analyse
    0.37
    Activations Density 0.002%

    No Known Activations