© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137234
    Prev
    Next
    INDEX
    Explanations

    made-up words or pseudo-words

    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_12_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
     η
    0.51
     prinsip
    0.49
     surroundings
    0.49
    τητας
    0.48
     comrades
    0.47
    thirds
    0.47
     geospatial
    0.46
    сида
    0.45
     APIDC
    0.45
     量
    0.45
    POSITIVE LOGITS
    label
    0.49
    custom
    0.47
    ASH
    0.47
    LOG
    0.46
    CK
    0.45
    UK
    0.44
    leather
    0.44
    RS
    0.41
     complète
    0.41
    unregister
    0.41
    Activations Density 0.012%

    No Known Activations