© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 14582
    Prev
    Next
    INDEX
    Explanations

    social constructivism, scaffolding, interaction

    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
     disappointments
    0.42
    几十
    0.39
     thicknesses
    0.39
     ['*.
    0.39
    煮
    0.39
    泱
    0.37
     boiled
    0.37
     ifstream
    0.37
     nause
    0.36
    selectbox
    0.36
    POSITIVE LOGITS
     scaffolding
    0.46
    hh
    0.42
    荕
    0.42
    Bb
    0.41
     chat
    0.41
     Zone
    0.40
     scaffolds
    0.40
     चैट
    0.40
     Soviet
    0.39
     Interaction
    0.39
    Activations Density 0.012%

    No Known Activations