© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 152440
    Prev
    Next
    INDEX
    Explanations

    `++` after `i`

    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_23_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
    thebetterindia
    0.37
    Swiss
    0.37
     Braunsch
    0.37
     kv
    0.36
    Fried
    0.36
    <unused322>
    0.36
    abhavena
    0.35
    affe
    0.35
    ヂ
    0.35
    sourceIP
    0.35
    POSITIVE LOGITS
     rayas
    0.46
     estrellas
    0.45
    萼
    0.44
    мон
    0.42
     estoque
    0.42
     versões
    0.42
     carreteras
    0.41
     productos
    0.40
     comenc
    0.40
     negocios
    0.39
    Activations Density 0.000%

    No Known Activations