© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 51171
    Prev
    Next
    INDEX
    Explanations

    ://

    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_55_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
     WON
    0.39
     grass
    0.37
    欢
    0.37
     budding
    0.36
     ஆண்
    0.34
     Huo
    0.34
    חות
    0.34
    찡
    0.33
    რთ
    0.33
    娇
    0.33
    POSITIVE LOGITS
     texas
    0.46
     philippines
    0.45
    ."},
    0.41
     malaysia
    0.40
    snd
    0.38
    抨
    0.38
    mtr
    0.37
    orcid
    0.37
    探测
    0.36
    paul
    0.36
    Activations Density 0.002%

    No Known Activations