© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 150516
    Prev
    Next
    INDEX
    Explanations

    Ob

    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_60_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
    THE
    0.49
    व
    0.43
    टोन
    0.41
    是非
    0.40
    ionized
    0.40
     THE
    0.39
    Renk
    0.38
    solved
    0.38
    }_{+}
    0.37
    VOLUME
    0.37
    POSITIVE LOGITS
    gv
    0.45
     for
    0.44
     privato
    0.41
     ін
    0.40
     För
    0.40
    єн
    0.40
    kv
    0.40
     chiaro
    0.40
     NPV
    0.39
     scrivere
    0.39
    Activations Density 0.000%

    No Known Activations