© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10441
    Prev
    Next
    INDEX
    Explanations

    statements of uncertainty or problems, especially related to mechanical issues

    oai_token-act-pair · gemini-2.0-flash

    malfunctions and errors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    sch
    -0.45
    @
    -0.45
    unis
    -0.44
     Great
    -0.43
    getActive
    -0.43
     tasas
    -0.40
    луй
    -0.40
    tek
    -0.40
    Great
    -0.39
    бира
    -0.39
    POSITIVE LOGITS
     חיצוניים
    0.86
     MainAxisSize
    0.79
    ISupport
    0.77
     actionMode
    0.75
    StoryboardSegue
    0.75
    AddTagHelper
    0.73
     صوتيه
    0.71
     AssemblyCulture
    0.71
    WriteBarrier
    0.71
     Autorizaciones
    0.70
    Activations Density 2.298%

    No Known Activations