© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13773
    Prev
    Next
    INDEX
    Explanations

    gang, violence, meter, Centre, artisanal, avocado, dollar

    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_13_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
    ala
    0.43
    ietro
    0.40
    იმ
    0.40
     intermolecular
    0.39
    𝖚
    0.38
    embeddings
    0.38
    下单
    0.38
     Elastic
    0.37
    adidas
    0.37
     dnia
    0.37
    POSITIVE LOGITS
     alimentación
    0.43
     Ç
    0.40
     kerosene
    0.39
     संवै
    0.39
    alimentation
    0.38
     breakfasts
    0.38
     alimentation
    0.38
    AutoHide
    0.37
     күз
    0.37
    筤
    0.37
    Activations Density 0.020%

    No Known Activations