© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 47564
    Prev
    Next
    INDEX
    Explanations

    and

    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_10_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
    I
    0.52
    ది
    0.48
    да
    0.47
    en
    0.41
    da
    0.41
    ISH
    0.41
    That
    0.40
    ASK
    0.39
    UDE
    0.38
    that
    0.38
    POSITIVE LOGITS
    }{
    0.49
    ב
    0.47
     \\
    0.44
    }}{
    0.44
     \
    0.44
    )|
    0.42
    }=
    0.42
     ۶
    0.42
     वर्ष
    0.42
    :
    0.42
    Activations Density 0.041%

    No Known Activations