© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 162946
    Prev
    Next
    INDEX
    Explanations

    number or list item

    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_31_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
     க்கு
    0.40
    מי
    0.38
    reon
    0.38
    ྐ
    0.37
     soiled
    0.36
     banknote
    0.36
     विश्वसनीयता
    0.35
    ذك
    0.35
    </tfoot>
    0.34
     reused
    0.34
    POSITIVE LOGITS
     Anas
    0.37
    Tomas
    0.37
    ˇ
    0.35
     Ruth
    0.34
    Ruth
    0.34
    してしまう
    0.33
     γεγον
    0.33
     Anfang
    0.33
    izzie
    0.33
    😻
    0.32
    Activations Density 0.005%

    No Known Activations