© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 80615
    Prev
    Next
    INDEX
    Explanations

    estimated pricing

    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_31_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
    ozz
    0.47
    uther
    0.38
    👱
    0.36
    VAT
    0.36
    🙎
    0.36
     પ્રો
    0.36
    ៤
    0.35
    valve
    0.34
    Њ
    0.33
    Translatef
    0.33
    POSITIVE LOGITS
     dop
    0.44
     lub
    0.43
     lubricants
    0.40
     mar
    0.37
     masquer
    0.37
     (?
    0.36
     DP
    0.36
    كري
    0.35
     epi
    0.34
     dopamine
    0.34
    Activations Density 0.003%

    No Known Activations