© 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. 17930
    Prev
    Next
    INDEX
    Explanations

    more than you think

    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
    Dade
    0.37
    ggac
    0.36
     മഹാ
    0.36
    훨
    0.35
    mdat
    0.35
     läht
    0.35
    WICK
    0.35
    蔓
    0.35
    更多
    0.34
    ।"
    0.34
    POSITIVE LOGITS
     indicated
    0.47
     hoped
    0.45
     anticipated
    0.44
     indicato
    0.41
     indica
    0.41
    맥
    0.39
     Sug
    0.39
     anticipates
    0.39
    '=>'','
    0.39
     Meinung
    0.38
    Activations Density 0.060%

    No Known Activations