© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 206149
    Prev
    Next
    INDEX
    Explanations

    feeling or state

    np_max-act-logits · gemini-2.5-flash-lite
    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
    HORIZONTAL
    0.40
     br
    0.39
     আজকের
    0.38
     pra
    0.38
    getahuan
    0.37
    투자
    0.36
     sm
    0.36
    ==========
    0.36
     burnt
    0.35
    ົມ
    0.35
    POSITIVE LOGITS
     feeling
    0.59
     certain
    0.58
     Feeling
    0.57
    feeling
    0.56
    Feeling
    0.53
    Certain
    0.50
     Certain
    0.50
    certain
    0.45
    一定
    0.44
     certaine
    0.43
    Activations Density 0.004%

    No Known Activations