© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 206302
    Prev
    Next
    INDEX
    Explanations

    he

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     gan
    0.53
     Hari
    0.43
    彼
    0.41
    gan
    0.40
     am
    0.38
    Hari
    0.38
     Gan
    0.37
     ganh
    0.37
     today
    0.36
    Gan
    0.36
    POSITIVE LOGITS
     he
    2.09
    เข
    1.69
    he
    1.67
    He
    1.56
    他
    1.52
     He
    1.51
     він
    1.48
     HE
    1.45
     он
    1.36
    HE
    1.28
    Activations Density 0.000%

    No Known Activations