© 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. 77616
    Prev
    Next
    INDEX
    Explanations

    actions and words

    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
    廼
    0.41
    দায়
    0.36
    お届け
    0.36
    <0xC2>
    0.34
    שא
    0.34
     پکڑ
    0.34
     étapes
    0.32
    Disposition
    0.32
    AKES
    0.32
    Colonne
    0.31
    POSITIVE LOGITS
    さん
    0.37
    ),\
    0.35
     FIS
    0.35
     完全
    0.35
    に対して
    0.34
     عليك
    0.34
     ಸ್ವ
    0.34
    aktoren
    0.33
     યોગ
    0.33
    )-$
    0.33
    Activations Density 0.069%

    No Known Activations