© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 147379
    Prev
    Next
    INDEX
    Explanations

    rap battles

    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_59_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
     Lili
    0.43
     Lille
    0.38
    ்களில்
    0.37
     माही
    0.37
    ASI
    0.37
    Lily
    0.35
    tren
    0.35
    )']
    0.35
    biggr
    0.35
     தரி
    0.35
    POSITIVE LOGITS
     prime
    0.51
     Prime
    0.44
     PRIME
    0.40
     Jihad
    0.39
    Prime
    0.39
    ThreadGroup
    0.39
    㹮
    0.38
     Early
    0.38
    㴼
    0.36
     bato
    0.36
    Activations Density 0.002%

    No Known Activations