© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 253856
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     aged
    0.43
    летним
    0.38
     éx
    0.38
     Aged
    0.37
    *}{
    0.37
    Claims
    0.37
    Claim
    0.36
    aged
    0.36
    }/>
    0.36
    Commonwealth
    0.36
    POSITIVE LOGITS
     lift
    0.59
     Lift
    0.55
     lifts
    0.45
    lift
    0.45
     lifted
    0.44
    Lift
    0.39
     Conn
    0.38
     мало
    0.37
    urney
    0.37
     Dec
    0.37
    Activations Density 0.000%

    No Known Activations