© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231486
    Prev
    Next
    INDEX
    Explanations

    marble diagrams

    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_6_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
    ants
    1.17
    how
    1.15
    و
    1.13
    at
    1.12
    ch
    1.10
    kons
    1.08
    why
    1.07
    hr
    1.06
    itation
    1.05
    it
    1.05
    POSITIVE LOGITS
     bullpen
    1.05
    h
    1.02
     。
    0.96
     countertop
    0.91
     kamera
    0.90
     nasc
    0.90
     subalgebra
    0.89
     hologram
    0.89
     trampoline
    0.89
     conver
    0.88
    Activations Density 0.000%

    No Known Activations