© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 81856
    Prev
    Next
    INDEX
    Explanations

    something else

    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_53_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
    लोत
    0.40
     ውስ
    0.38
    髅
    0.37
    翮
    0.37
     looping
    0.37
    撅
    0.37
    ovie
    0.36
     জো
    0.36
     nonzero
    0.36
    折扣
    0.36
    POSITIVE LOGITS
    bj
    0.41
    汪
    0.38
    氏
    0.37
     స్టే
    0.36
     scales
    0.36
    情
    0.36
     tận
    0.35
    omel
    0.35
    ASHI
    0.35
    രി
    0.35
    Activations Density 0.000%

    No Known Activations