© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 207344
    Prev
    Next
    INDEX
    Explanations

    admission standards or specific processors

    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_19_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
    iellement
    0.39
    ോ
    0.39
    राजनी
    0.39
    듈
    0.38
    uf
    0.37
    dj
    0.37
    äl
    0.36
    িমের
    0.36
     lekk
    0.36
    लॉक
    0.36
    POSITIVE LOGITS
     scap
    0.38
    }:=
    0.37
    Testing
    0.36
    CMI
    0.36
     unreal
    0.36
     carpet
    0.36
     pytest
    0.35
     назначения
    0.35
     CallbackContext
    0.35
     Precambrian
    0.35
    Activations Density 0.010%

    No Known Activations