© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 96998
    Prev
    Next
    INDEX
    Explanations

    Museums in Spain and Netherlands

    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_14_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
    Biblioteca
    0.64
    𒌨
    0.60
    StatusCode
    0.59
     Beaucoup
    0.57
    économ
    0.55
     ricerca
    0.54
    UFF
    0.53
    ፖ
    0.53
    ards
    0.52
    িতের
    0.52
    POSITIVE LOGITS
     उसने
    0.50
     arteries
    0.48
     Toronto
    0.47
    这不是
    0.46
    这就是
    0.46
     Rhythm
    0.46
     Xing
    0.46
     hyperplasia
    0.45
     ему
    0.44
    节奏
    0.44
    Activations Density 0.000%

    No Known Activations