© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 18079
    Prev
    Next
    INDEX
    Explanations

    version numbers and xml tags

    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_34_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
     შეუ
    0.41
     Теле
    0.41
    HideFlags
    0.39
     सर्विस
    0.38
     Güzel
    0.38
     nevez
    0.37
     millioner
    0.37
    屠
    0.37
     इसलिये
    0.36
     permanently
    0.36
    POSITIVE LOGITS
     extra
    0.39
     bulge
    0.38
     debris
    0.38
     cured
    0.37
     vents
    0.37
     traje
    0.37
     open
    0.36
     UAE
    0.35
    gpu
    0.35
     drains
    0.35
    Activations Density 0.000%

    No Known Activations