© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14043
    Prev
    Next
    INDEX
    Explanations

    loading model from hub

    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_15_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
    ступ
    0.15
     bushel
    0.15
     situação
    0.15
     οπο
    0.15
    ɳ
    0.14
    বৃত্ত
    0.14
    等级
    0.14
    AppBarLayout
    0.14
     raio
    0.14
     situações
    0.14
    POSITIVE LOGITS
    ግዳ
    0.17
    ቭ
    0.17
    された
    0.17
    гой
    0.16
     날
    0.16
     Priv
    0.16
    GEN
    0.15
     നിര്‍
    0.15
    ེ་
    0.15
    τών
    0.15
    Activations Density 0.009%

    No Known Activations