© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 52628
    Prev
    Next
    INDEX
    Explanations

    probability, distribution, range

    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_30_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
    ichtung
    0.40
     Human
    0.35
     Heir
    0.35
     denominators
    0.35
    摜
    0.35
     Foy
    0.35
    Ẹ
    0.35
     human
    0.34
     estrat
    0.34
    Human
    0.34
    POSITIVE LOGITS
    统一
    0.37
    ారణ
    0.35
    鈳
    0.35
    紓
    0.35
     deserialize
    0.34
     plast
    0.34
     освобо
    0.34
    纾
    0.34
     translate
    0.33
    未经
    0.33
    Activations Density 0.007%

    No Known Activations