© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3572
    Prev
    Next
    INDEX
    Explanations

    plot holes, pacing, flow

    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_39_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
    🔐
    0.36
    }$}
    0.36
     പ്രവര്‍ത്തന
    0.36
    graf
    0.36
    玠
    0.35
    Align
    0.35
    ᱡ
    0.34
    ᾷ
    0.34
    align
    0.33
     Nxb
    0.33
    POSITIVE LOGITS
     pacing
    0.51
    উদ
    0.38
     awkward
    0.38
     dan
    0.38
    Frequency
    0.38
     पू
    0.37
     buses
    0.37
     microtub
    0.36
    sterreich
    0.36
     पूर्णा
    0.36
    Activations Density 0.194%

    No Known Activations