© 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. 178996
    Prev
    Next
    INDEX
    Explanations

    sequences after 'and'

    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
    ❣️
    0.38
     처
    0.37
     dailySales
    0.36
     compressive
    0.35
    🔯
    0.34
     candidates
    0.34
    🍐
    0.34
     devast
    0.33
     payouts
    0.33
     💕
    0.33
    POSITIVE LOGITS
     Mosley
    0.42
     moderne
    0.40
    istosoma
    0.39
    uitary
    0.39
    Us
    0.38
     बीन
    0.38
     bate
    0.38
    Ne
    0.38
     spesso
    0.37
    chien
    0.37
    Activations Density 0.000%

    No Known Activations