© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 42786
    Prev
    Next
    INDEX
    Explanations

    Ocean and coastal descriptions

    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_13_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
    世話
    0.29
    ract
    0.27
    ttes
    0.26
    ্স
    0.26
    sembled
    0.25
    ransport
    0.25
    ༅
    0.25
    팅
    0.25
    ss
    0.25
    rumah
    0.24
    POSITIVE LOGITS
     –
    0.31
    ’
    0.29
    Pclass
    0.27
     প্রত্যাখ্যান
    0.26
     precondition
    0.25
    एन
    0.25
     \
    0.24
     LEE
    0.24
     ballpark
    0.24
     p
    0.24
    Activations Density 0.025%

    No Known Activations