© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 5440
    Prev
    Next
    INDEX
    Explanations

    high

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
    ovaní
    0.38
    璫
    0.36
     वाणी
    0.35
    栨
    0.35
    вета
    0.35
     وإ
    0.35
    творення
    0.34
    袁
    0.34
     ولا
    0.34
    暮らし
    0.34
    POSITIVE LOGITS
     level
    0.49
     levels
    0.47
     nivel
    0.43
    level
    0.42
     niveles
    0.42
    jacking
    0.40
     sum
    0.40
     indag
    0.40
    )<
    0.40
     nível
    0.40
    Activations Density 0.082%

    No Known Activations