© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 78573
    Prev
    Next
    INDEX
    Explanations

    programming languages and systems

    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_29_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
     mesela
    0.38
     prel
    0.37
     aby
    0.35
    acy
    0.35
     mx
    0.35
    }<\
    0.35
     say
    0.34
    的
    0.34
    比如
    0.34
     sah
    0.33
    POSITIVE LOGITS
    че
    0.39
     بیٹ
    0.36
    ჟ
    0.35
    ́
    0.35
    ustration
    0.34
    StubCompat
    0.34
    เด
    0.34
    ançaise
    0.34
    ඔ
    0.34
     Ně
    0.33
    Activations Density 0.012%

    No Known Activations