© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 179874
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_24_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
    ऊस
    0.41
    weł
    0.39
    的基础上
    0.39
    दों
    0.39
     කරන
    0.38
    薷
    0.38
    荣耀
    0.37
    广场
    0.37
    كتب
    0.36
    Rab
    0.36
    POSITIVE LOGITS
    zu
    0.40
     holog
    0.40
     airbags
    0.37
     imprisoned
    0.37
     disent
    0.37
     assass
    0.37
     overd
    0.37
     serious
    0.36
    を一
    0.36
     understated
    0.36
    Activations Density 0.000%

    No Known Activations