© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 194853
    Prev
    Next
    INDEX
    Explanations

    ends with punctuation or end of turn

    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_27_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
    iku
    0.33
    iment
    0.33
    enser
    0.32
    imag
    0.32
    /:
    0.31
    avat
    0.31
     envisage
    0.31
    issions
    0.30
     vents
    0.30
    avras
    0.30
    POSITIVE LOGITS
     Gegensatz
    0.39
    少的
    0.37
    ፋ
    0.35
    မ်း
    0.35
     Publicity
    0.34
    jsce
    0.34
    ostante
    0.33
    惧
    0.33
     కలిసి
    0.33
    心中的
    0.33
    Activations Density 0.035%

    No Known Activations