© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 134857
    Prev
    Next
    INDEX
    Explanations

    "Kimi" followed by "ni" or "no"

    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_1_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
    .
    1.41
     ecz
    1.02
     proteína
    1.02
     at
    1.01
     teve
    1.01
     to
    0.98
     связан
    0.96
     orientado
    0.93
     scrotum
    0.91
     zvý
    0.91
    POSITIVE LOGITS
    in
    1.81
    ار
    1.69
    is
    1.52
    us
    1.51
    ل
    1.46
    ת
    1.45
    en
    1.39
    inhas
    1.33
    et
    1.30
    ان
    1.30
    Activations Density 0.000%

    No Known Activations