© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 11-GEMMASCOPE-2-TRANSCODER-262K
    4. 38218
    Prev
    Next
    INDEX
    Explanations

    Spanish and Portuguese place names

    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_11_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
    Interpreter
    0.23
    ﻔ
    0.22
    window
    0.21
    安卓
    0.21
    Important
    0.21
    Calend
    0.21
     anni
    0.20
    Classe
    0.20
    Helix
    0.20
    Correlation
    0.20
    POSITIVE LOGITS
     legjob
    0.22
     steaks
    0.21
    erk
    0.21
    eged
    0.21
    incy
    0.21
     zorgt
    0.20
    <0xB2>
    0.20
    aken
    0.20
    ovel
    0.20
     bolstering
    0.20
    Activations Density 0.006%

    No Known Activations