© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 237563
    Prev
    Next
    INDEX
    Explanations

    shortages and deficiencies

    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_25_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
     disgusted
    0.37
     reject
    0.36
     unhappy
    0.35
     stif
    0.34
    濁
    0.34
     Masse
    0.33
    腻
    0.33
     присут
    0.33
     disillusioned
    0.33
     accumulate
    0.33
    POSITIVE LOGITS
    ⃖
    0.40
    holz
    0.36
    enhuma
    0.34
    👧
    0.34
    nucleon
    0.33
    궪
    0.33
     vulner
    0.33
    bare
    0.32
    Gap
    0.32
    InitFlag
    0.32
    Activations Density 0.014%

    No Known Activations