© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 238018
    Prev
    Next
    INDEX
    Explanations

    social justice

    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_25_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
    厘
    0.37
     coverage
    0.36
    瑁
    0.35
     Ireland
    0.35
     Fiziki
    0.35
     starch
    0.34
     reda
    0.34
     plastics
    0.33
    <b>
    0.33
     literally
    0.33
    POSITIVE LOGITS
    Estos
    0.47
    ទ
    0.43
    Choisissez
    0.43
    athlon
    0.42
    }=(
    0.42
    ordnung
    0.41
    Esto
    0.41
    痨
    0.41
    })=\
    0.41
    algorithm
    0.41
    Activations Density 0.003%

    No Known Activations