© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242968
    Prev
    Next
    INDEX
    Explanations

    fall short

    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_40_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
     emplea
    0.44
    čili
    0.43
    vere
    0.38
     inver
    0.38
    俄
    0.38
    udal
    0.38
     চে
    0.37
    ymp
    0.37
    чат
    0.36
     allait
    0.36
    POSITIVE LOGITS
     Ahl
    0.42
    កើត
    0.40
    苼
    0.40
     قبول
    0.39
     reproducible
    0.39
     pü
    0.38
     ulang
    0.38
     Reinhold
    0.38
     soddis
    0.36
    ناه
    0.36
    Activations Density 0.002%

    No Known Activations