© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 220742
    Prev
    Next
    INDEX
    Explanations

    software tools like

    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_31_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
     !}
    0.43
     organización
    0.41
    吲
    0.39
    !}
    0.39
     Запад
    0.38
    なんと
    0.37
    }$(
    0.37
    駭
    0.37
     !!
    0.36
    !”
    0.36
    POSITIVE LOGITS
     Trips
    0.39
    ประโยชน์
    0.38
    healthy
    0.38
    ory
    0.36
     NSR
    0.36
    patient
    0.33
     Waiver
    0.33
    constraints
    0.33
    ained
    0.32
    elist
    0.32
    Activations Density 0.011%

    No Known Activations