© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 103103
    Prev
    Next
    INDEX
    Explanations

    colonoscopy

    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_1_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
    т
    1.26
    ד
    1.23
    д
    1.22
    ING
    1.20
    ו
    1.19
    ه
    1.16
     maliciously
    1.14
    ж
    1.12
    𝔀
    1.12
     negligently
    1.10
    POSITIVE LOGITS
    is
    1.52
    ia
    1.50
    ale
    1.43
    ala
    1.25
    n
    1.25
    </strong>
    1.21
    ore
    1.20
    r
    1.14
    <0x0D>
    1.13
    ii
    1.09
    Activations Density 0.000%

    No Known Activations