© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257823
    Prev
    Next
    INDEX
    Explanations

    touching or tangent contact

    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_22_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
     வட
    0.43
    และ
    0.43
     Bogotá
    0.42
     বাংলাদেশে
    0.41
     Catarina
    0.41
    西兰
    0.39
    ເຊ
    0.39
    શ
    0.39
     trùng
    0.38
     соци
    0.38
    POSITIVE LOGITS
     asper
    0.48
    ctions
    0.46
    ToObject
    0.44
    Nonce
    0.44
     peremptory
    0.43
    arious
    0.42
     不能
    0.42
    PatientR
    0.42
    ிகளில்
    0.42
     dispute
    0.42
    Activations Density 0.000%

    No Known Activations