© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 90059
    Prev
    Next
    INDEX
    Explanations

    latent semantic heat

    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_3_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
    t
    1.13
    I
    0.86
    f
    0.72
    و
    0.72
    an
    0.64
    Kappa
    0.61
    is
    0.60
    ai
    0.59
    u
    0.59
    ו
    0.59
    POSITIVE LOGITS
     Lat
    0.68
     LAT
    0.61
     học
    0.58
     ricevere
    0.58
    ATION
    0.57
     România
    0.57
     latin
    0.57
     inglês
    0.56
     of
    0.55
     của
    0.55
    Activations Density 0.001%

    No Known Activations