© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 5919
    Prev
    Next
    INDEX
    Explanations

    answer questions or generate text

    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_38_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
    Advantages
    0.44
     $+$
    0.41
     vantagens
    0.41
    )+(
    0.41
     плю
    0.41
    ＋
    0.41
    ")+
    0.41
     }+\
    0.40
     Advantages
    0.40
    >+</
    0.40
    POSITIVE LOGITS
    conciliation
    0.38
    稚
    0.37
    MS
    0.36
    Ill
    0.36
    liament
    0.36
     ...)
    0.35
    iteracy
    0.35
     Sim
    0.34
    concatenate
    0.34
     .
    0.33
    Activations Density 0.237%

    No Known Activations