© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31241
    Prev
    Next
    INDEX
    Explanations

    contain or contains

    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_31_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
    YT
    0.43
     yn
    0.36
     прид
    0.35
    ্ম
    0.35
     век
    0.35
     პარ
    0.35
    فو
    0.34
    ύ
    0.34
     ملاحظ
    0.34
    ologisk
    0.34
    POSITIVE LOGITS
     Contains
    0.63
    Contains
    0.63
    contains
    0.60
     contiene
    0.60
     contains
    0.59
     enthalten
    0.58
     Containing
    0.57
    含有
    0.56
     содержит
    0.56
     zawiera
    0.56
    Activations Density 0.028%

    No Known Activations