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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4702
    Prev
    Next
    INDEX
    Explanations

    transitions or conjunctions within a text

    oai_token-act-pair · gemini-2.0-flash

    auxiliary verbs and punctuation

    np_token-act-pair-logits · gpt-4o-mini

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    DataAnnotations
    -0.54
    ProgressHUD
    -0.51
     wasteland
    -0.47
     Utile
    -0.46
    qtype
    -0.45
     NEX
    -0.45
     ErrInvalid
    -0.44
    anyak
    -0.44
    возь
    -0.44
    BASELINE
    -0.44
    POSITIVE LOGITS
     autorytatywna
    0.76
     Does
    0.74
     lenker
    0.70
    Does
    0.70
     Are
    0.69
     does
    0.68
     Is
    0.68
     وتسجيلات
    0.63
    Are
    0.63
     are
    0.60
    Activations Density 1.523%

    No Known Activations