© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 81181
    Prev
    Next
    INDEX
    Explanations

    @ symbol followed by space or special characters

    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
     divulge
    0.35
    biet
    0.34
    ​,
    0.32
    ಿರ
    0.31
    Whitespace
    0.31
     ويب
    0.30
    句
    0.29
     के
    0.29
    干净
    0.29
    illing
    0.29
    POSITIVE LOGITS
     assertThat
    0.36
    ंशिक
    0.36
    മാണ
    0.35
     theres
    0.35
     rolled
    0.34
     fragmented
    0.33
    majority
    0.32
    াদেশিক
    0.32
     slept
    0.32
    ttet
    0.32
    Activations Density 0.000%

    No Known Activations