© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 62019
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    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_2_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
    ુ
    0.98
    ني
    0.96
    ưới
    0.95
     ballistic
    0.92
    㓞
    0.92
    ের
    0.92
     significative
    0.91
     is
    0.91
     conseguir
    0.90
     communauté
    0.89
    POSITIVE LOGITS
    i
    2.23
    I
    1.70
    y
    1.66
    ו
    1.65
    in
    1.61
    F
    1.59
    י
    1.44
    at
    1.41
    en
    1.39
    u
    1.38
    Activations Density 0.000%

    No Known Activations