© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 249289
    Prev
    Next
    INDEX
    Explanations

    actions and media

    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_56_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
     ca
    0.54
     Ca
    0.47
     caul
    0.45
    ca
    0.40
    Ca
    0.39
     cauliflower
    0.36
    —
    0.35
     covering
    0.35
     cae
    0.35
     duk
    0.34
    POSITIVE LOGITS
    𝖚
    0.35
    Albums
    0.35
     Слова
    0.35
     Albums
    0.35
    Mi
    0.34
    ņa
    0.34
     Album
    0.33
    TeX
    0.32
    راعظم
    0.32
     Words
    0.32
    Activations Density 0.001%

    No Known Activations