© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 80813
    Prev
    Next
    INDEX
    Explanations

    best option

    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_53_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
     indiscrimin
    0.40
     रमा
    0.37
     Leider
    0.36
    さま
    0.33
     contingencies
    0.33
    rard
    0.33
     liberty
    0.32
     요
    0.32
    िल्म
    0.32
     よ
    0.31
    POSITIVE LOGITS
     Capsule
    0.35
    RECORD
    0.35
     سوریه
    0.35
    Hyper
    0.35
    OGRAPHY
    0.35
     بوا
    0.35
     NA
    0.34
     z
    0.34
     Zav
    0.34
    潙
    0.33
    Activations Density 0.001%

    No Known Activations