© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 42465
    Prev
    Next
    INDEX
    Explanations

    connecting code

    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_22_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
    úcar
    0.41
    吘
    0.41
     अरे
    0.40
    àu
    0.40
    叩
    0.39
     reimag
    0.38
     stabbing
    0.37
     やつ
    0.37
     идти
    0.37
    哚
    0.37
    POSITIVE LOGITS
     initialise
    0.47
    Initialization
    0.46
     bott
    0.44
     contingencies
    0.42
    marginY
    0.42
     organisational
    0.40
    接近
    0.40
    Ltd
    0.40
    میم
    0.39
    ঋ
    0.39
    Activations Density 0.000%

    No Known Activations