© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 194097
    Prev
    Next
    INDEX
    Explanations

    sender/source identification

    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_27_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
    getBy
    0.43
    фф
    0.42
     linear
    0.40
    пов
    0.38
     obtem
    0.38
     progenitor
    0.38
    𝔾
    0.38
     वह
    0.37
    про
    0.37
    нтэр
    0.37
    POSITIVE LOGITS
    <unused0>
    0.46
    溲
    0.43
     ومش
    0.41
     Likely
    0.40
    焦
    0.39
     تح
    0.39
     verhaal
    0.38
     داستان
    0.36
     न्यायालया
    0.36
     اخبار
    0.36
    Activations Density 0.000%

    No Known Activations