© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 51176
    Prev
    Next
    INDEX
    Explanations

    doi links

    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_30_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
    InterfaceLine
    0.51
    MinIntensity
    0.45
     currentUser
    0.42
     ★★
    0.41
    AttributedString
    0.41
     insulina
    0.40
    صیٰ
    0.40
     wichtigsten
    0.40
    ূনতম
    0.39
    DeathRecord
    0.39
    POSITIVE LOGITS
    0.42
    can
    0.40
    id
    0.40
    ust
    0.39
    ally
    0.38
     Accom
    0.38
      
    0.37
    al
    0.37
     al
    0.37
     A
    0.36
    Activations Density 0.000%

    No Known Activations