© 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. 208624
    Prev
    Next
    INDEX
    Explanations

    Dutch places

    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
    处
    0.46
    consciously
    0.40
    ariyati
    0.40
    尚
    0.40
    處
    0.40
    责
    0.39
    odym
    0.38
    責
    0.38
    ंद्र
    0.38
    stan
    0.37
    POSITIVE LOGITS
    itação
    0.39
     conf
    0.37
    Validated
    0.37
     nem
    0.37
     hw
    0.37
     popul
    0.36
    Verification
    0.35
    Hor
    0.35
    hun
    0.35
    Validation
    0.34
    Activations Density 0.001%

    No Known Activations