© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 126754
    Prev
    Next
    INDEX
    Explanations

    dashboard or dashcam

    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_37_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
     aeroplane
    0.39
    泳
    0.39
    荿
    0.38
    }$=
    0.38
     Mayer
    0.37
     మూ
    0.37
     overgrown
    0.36
    legenheit
    0.36
    ∋
    0.36
    మూ
    0.36
    POSITIVE LOGITS
     dash
    1.02
     Dash
    0.92
    Dash
    0.91
     dashboard
    0.86
     डैश
    0.85
    dash
    0.84
     dashboards
    0.84
     dashes
    0.84
    Dashboard
    0.81
     Dashboard
    0.80
    Activations Density 0.001%

    No Known Activations