© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 119059
    Prev
    Next
    INDEX
    Explanations

    a [followed by] approach/variable/method

    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
     equivoc
    0.28
     piensan
    0.27
    ாலி
    0.26
     gleichen
    0.26
    ̪
    0.26
     bewegen
    0.26
     equator
    0.25
     remembrance
    0.25
    考えて
    0.25
     sensi
    0.25
    POSITIVE LOGITS
    utt
    0.29
    för
    0.27
    ared
    0.27
    覷
    0.26
     scott
    0.26
    uct
    0.26
    緊
    0.26
    FIND
    0.26
    erné
    0.26
    ilt
    0.25
    Activations Density 0.015%

    No Known Activations