© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31889
    Prev
    Next
    INDEX
    Explanations

    sea 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_31_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
     lak
    0.46
    溯
    0.40
    Swan
    0.38
    astore
    0.38
    滹
    0.38
    𝐏
    0.37
    endt
    0.37
     İli
    0.37
     sklep
    0.36
    店家
    0.36
    POSITIVE LOGITS
     seashell
    0.40
    Coastal
    0.39
     oceanic
    0.37
     coastal
    0.37
    щем
    0.37
    Gm
    0.36
     seaside
    0.36
    Qg
    0.36
    
    0.36
     prognostic
    0.35
    Activations Density 0.022%

    No Known Activations