© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11343
    Prev
    Next
    INDEX
    Explanations

    HBO or operating systems

    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
    गेशन
    0.50
     सोनू
    0.47
    }</
    0.47
    रण
    0.45
    गत
    0.44
    私の
    0.44
     foreigner
    0.44
    ಟ
    0.44
    ṟ
    0.44
    اتا
    0.43
    POSITIVE LOGITS
     instinct
    0.51
     quotient
    0.50
     instincts
    0.49
     મૂ
    0.48
     précie
    0.47
     sú
    0.47
    菠
    0.47
     gut
    0.47
     bakal
    0.46
    ี
    0.46
    Activations Density 0.030%

    No Known Activations