© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 38819
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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_57_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
    ້ງ
    0.39
     प्राइम
    0.38
     afuera
    0.37
    ⺀
    0.37
     afară
    0.36
    Famil
    0.36
    earic
    0.36
     PRIME
    0.36
    ή
    0.36
    Ợ
    0.35
    POSITIVE LOGITS
    दु
    0.41
     Dealing
    0.39
    ગ્ર
    0.38
    濫
    0.37
    icana
    0.37
    akt
    0.35
    Dealing
    0.35
    令人
    0.34
    Dana
    0.34
     acetaldehyde
    0.34
    Activations Density 0.000%

    No Known Activations