© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 208320
    Prev
    Next
    INDEX
    Explanations

    1

    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_56_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
     WaitFor
    0.39
     ]:
    0.38
    𝗞
    0.38
     pove
    0.37
    кна
    0.37
    Phantom
    0.36
    RESSION
    0.36
    Website
    0.35
    Rows
    0.34
    ▋
    0.34
    POSITIVE LOGITS
    sted
    0.42
    stum
    0.41
    st
    0.41
    std
    0.38
    stes
    0.38
    blend
    0.38
    iving
    0.37
    stw
    0.37
    stp
    0.37
    sten
    0.35
    Activations Density 0.003%

    No Known Activations