© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 89850
    Prev
    Next
    INDEX
    Explanations

    identifying planning factors

    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_11_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
     in
    0.59
    #
    0.55
    一大
    0.53
    fall
    0.52
    case
    0.51
    by
    0.51
    fetch
    0.51
    কে
    0.50
    ‘
    0.49
    the
    0.49
    POSITIVE LOGITS
    ൃ
    0.66
    𒉿
    0.64
    ㄶ
    0.62
    恹
    0.59
    ㅆ
    0.55
     экономического
    0.55
    𝘀
    0.55
    мни
    0.54
     sicurezza
    0.54
    okhlov
    0.54
    Activations Density 0.001%

    No Known Activations