© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174307
    Prev
    Next
    INDEX
    Explanations

    membrane related dynamics

    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_20_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
    蘊
    0.46
     መጠን
    0.45
    راجع
    0.44
    سون
    0.42
    ｢
    0.42
    ření
    0.41
    쭤
    0.41
     প্রশিক্ষণ
    0.41
    学的
    0.41
    ጷ
    0.40
    POSITIVE LOGITS
     podrían
    0.41
     mistrust
    0.41
    ຕ່
    0.40
     Mark
    0.40
    arma
    0.40
     distrust
    0.40
     numerosas
    0.39
     dekat
    0.38
    rid
    0.38
     Attention
    0.38
    Activations Density 0.001%

    No Known Activations