© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 33117
    Prev
    Next
    INDEX
    Explanations

    code comments

    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_31_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
    اهده
    0.28
    ۇر
    0.28
    }^{\
    0.27
    គ
    0.27
    jeuner
    0.27
    MARINE
    0.27
    )(\
    0.26
    )_
    0.26
    umes
    0.25
    },-
    0.25
    POSITIVE LOGITS
    试验
    0.34
     personaggi
    0.32
     отзывы
    0.31
     Fußball
    0.30
    ˝
    0.30
    jährige
    0.29
     años
    0.29
    ILING
    0.29
    BleStatus
    0.29
    φέ
    0.29
    Activations Density 0.004%

    No Known Activations