© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257811
    Prev
    Next
    INDEX
    Explanations

    capitals or major cities

    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_22_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
     Роди
    0.36
    Population
    0.35
     coyote
    0.35
    शांत
    0.35
    थ
    0.33
    🫤
    0.33
    उंड
    0.33
     मंदिर
    0.33
    ርስ
    0.32
    Pergunta
    0.32
    POSITIVE LOGITS
     hydrocarbon
    0.41
     o
    0.38
     oil
    0.38
     splashing
    0.38
     huv
    0.37
     si
    0.37
     sis
    0.37
     splashes
    0.37
    len
    0.36
    chosen
    0.35
    Activations Density 0.000%

    No Known Activations