© 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. 23376
    Prev
    Next
    INDEX
    Explanations

    cityscapes and night

    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
     landscapes
    0.42
     Landscapes
    0.42
    Land
    0.40
    艱
    0.38
    ępuje
    0.38
    䅐
    0.37
     τρί
    0.36
    紀念
    0.36
    Salv
    0.35
    nienia
    0.35
    POSITIVE LOGITS
     Se
    0.61
    Se
    0.53
     city
    0.43
     фигу
    0.43
    city
    0.42
    se
    0.42
     கோவை
    0.39
     sk
    0.39
     City
    0.39
    즉
    0.39
    Activations Density 0.053%

    No Known Activations