© 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-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1968
    Prev
    Next
    INDEX
    Explanations

    question and answer exchanges in a chat

    oai_token-act-pair · gemini-2.0-flash

    code snippets/foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    новниш
    -0.86
     Normdatei
    -0.84
     Numerade
    -0.79
     lenker
    -0.74
    rungsseite
    -0.72
    Autoritní
    -0.72
     Roskov
    -0.71
    ⓧ
    -0.69
    Diwedd
    -0.69
    expandindo
    -0.69
    POSITIVE LOGITS
     capacities
    0.55
     absc
    0.47
     laminar
    0.45
     fibroblasts
    0.43
     fibroblast
    0.42
     confinement
    0.42
     lymphoid
    0.42
     resins
    0.41
     Incar
    0.41
     lamina
    0.41
    Activations Density 0.427%

    No Known Activations