© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 34951
    Prev
    Next
    INDEX
    Explanations

    forgetting or limitation

    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
     jacuzzi
    0.40
     Bellamy
    0.39
    tyw
    0.38
    훈
    0.38
    ydia
    0.38
    Jur
    0.38
     Alexandra
    0.38
    loor
    0.38
     whirlpool
    0.37
     regenerative
    0.36
    POSITIVE LOGITS
     sanity
    0.44
    sanity
    0.39
     আরোপিত
    0.39
    鹽
    0.37
     sane
    0.37
     sentences
    0.35
    盐
    0.34
    white
    0.34
     humane
    0.34
    <unused18>
    0.33
    Activations Density 0.073%

    No Known Activations