© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 93513
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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_60_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
     Э
    1.80
     Έ
    1.64
     الا
    1.63
    Ek
    1.50
     Ek
    1.48
     Эк
    1.45
     Em
    1.41
    Em
    1.41
     Eq
    1.35
    Eq
    1.35
    POSITIVE LOGITS
    え
    0.59
    える
    0.46
     eum
    0.45
     eus
    0.44
     えっ
    0.40
     echelon
    0.40
     eax
    0.39
     euc
    0.39
     え
    0.38
    efully
    0.38
    Activations Density 0.083%

    No Known Activations