© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 196884
    Prev
    Next
    INDEX
    Explanations

    fail

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    eliness
    0.42
     Lyn
    0.39
     cover
    0.39
     Clothes
    0.37
     Od
    0.37
    рам
    0.37
    ணைய
    0.37
    }->
    0.36
     HP
    0.36
    коло
    0.36
    POSITIVE LOGITS
    udan
    0.41
     olmadığını
    0.40
    상을
    0.39
    ならない
    0.39
     배워
    0.38
    never
    0.38
     এদিন
    0.38
     মহাশয়
    0.38
    𝘔
    0.38
    Never
    0.37
    Activations Density 0.002%

    No Known Activations