© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53257
    Prev
    Next
    INDEX
    Explanations

    color codes, padding, margin

    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_31_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
     Apple
    0.41
     앞
    0.40
    front
    0.38
     அனை
    0.38
    앞
    0.38
     Sar
    0.37
     frente
    0.37
     Jawa
    0.36
     União
    0.36
    переди
    0.36
    POSITIVE LOGITS
    рной
    0.40
    レーター
    0.38
     tailed
    0.37
    ት
    0.37
    Restriction
    0.36
    AbsolutePath
    0.36
    畯
    0.35
    鱸
    0.35
    后者
    0.35
    मित्र
    0.34
    Activations Density 0.001%

    No Known Activations