© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 77902
    Prev
    Next
    INDEX
    Explanations

    compared to

    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
     dez
    0.40
    劣
    0.37
     (§
    0.36
    PP
    0.36
     Sor
    0.36
    饰
    0.36
     Dez
    0.35
     스스로
    0.35
    해서
    0.35
    sor
    0.35
    POSITIVE LOGITS
    ವಿಲ್ಲ
    0.41
    uega
    0.41
     बल्ले
    0.40
    removeAttribute
    0.40
    䒽
    0.40
    မဟုတ်
    0.38
     matematica
    0.38
     MATHEMAT
    0.37
     geen
    0.37
     vez
    0.36
    Activations Density 0.002%

    No Known Activations