© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 97667
    Prev
    Next
    INDEX
    Explanations

    configuration settings and code configuration

    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_14_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
     rocket
    0.13
     jeune
    0.13
    <strong>
    0.12
     Whereas
    0.12
     πλα
    0.12
     aikana
    0.12
    Korea
    0.12
    },
    0.12
     llam
    0.12
    Kernel
    0.12
    POSITIVE LOGITS
    бели
    0.14
    веду
    0.14
     لوبه
    0.14
    డో
    0.14
    𝓖
    0.14
    ર્મ
    0.13
    лору
    0.13
    outputPath
    0.13
    𝓭
    0.13
    وري
    0.13
    Activations Density 0.010%

    No Known Activations