© 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. 93471
    Prev
    Next
    INDEX
    Explanations

    places

    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
     항
    0.43
     eb
    0.40
    ştir
    0.40
    ᅡ
    0.39
     calibrate
    0.38
    항
    0.37
     prov
    0.37
    iob
    0.37
    象
    0.37
     abst
    0.36
    POSITIVE LOGITS
     St
    0.58
    St
    0.44
     Thông
    0.42
     Ста
    0.42
     Semiconductor
    0.42
     Autumn
    0.41
     ক্যাথ
    0.41
    ORS
    0.41
     Insulin
    0.41
     Sousa
    0.40
    Activations Density 0.000%

    No Known Activations