© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 113001
    Prev
    Next
    INDEX
    Explanations

    x.y.z version notation

    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_2_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
    ق
    1.02
    </h6>
    0.93
    <0x0D>
    0.93
    </h3>
    0.91
     České
    0.89
    </sup>
    0.85
     powied
    0.85
    어
    0.84
    كس
    0.83
    خ
    0.83
    POSITIVE LOGITS
     to
    1.16
    9
    0.96
     by
    0.93
     handlebar
    0.92
    were
    0.89
    rutt
    0.86
    siniz
    0.85
    dance
    0.85
     there
    0.83
     them
    0.83
    Activations Density 0.009%

    No Known Activations