© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 53515
    Prev
    Next
    INDEX
    Explanations

    example

    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
     kut
    0.29
     φ
    0.29
     ben
    0.29
     voisin
    0.29
     ingenious
    0.28
    シック
    0.28
     wartime
    0.28
     대신
    0.27
     vain
    0.27
     Within
    0.27
    POSITIVE LOGITS
    similar
    0.34
     подобных
    0.33
    𒀀
    0.33
     podob
    0.32
     similar
    0.31
     подоб
    0.31
     ähn
    0.31
     выяв
    0.30
    Affected
    0.29
    Classes
    0.29
    Activations Density 0.014%

    No Known Activations