© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 105895
    Prev
    Next
    INDEX
    Explanations

    bottles

    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_1_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
    प
    1.22
    its
    1.18
    D
    1.18
    ש
    1.18
    G
    1.17
    न
    1.14
    ’
    1.09
    _
    1.08
    지
    1.05
    가
    1.05
    POSITIVE LOGITS
    ל
    1.24
    ת
    1.05
     refleja
    1.00
     predom
    0.96
     moze
    0.96
     zelo
    0.94
     preved
    0.93
    كبر
    0.93
     subscrib
    0.92
     documento
    0.92
    Activations Density 0.001%

    No Known Activations