© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11446
    Prev
    Next
    INDEX
    Explanations

    variations of the prefix "Cer" or "Ker"

    oai_token-act-pair · gemini-2.0-flash

    words starting with 'Cer'

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

    Cer

    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
    ngdoc
    -0.60
    پیوند
    -0.57
    surate
    -0.56
     Vordergrund
    -0.56
    ్వ
    -0.54
    InitStruct
    -0.52
    rines
    -0.51
     nargin
    -0.51
    ctez
    -0.50
     Bort
    -0.50
    POSITIVE LOGITS
     виправивши
    0.54
    IUrlHelper
    0.53
    Hochspringen
    0.52
    ząt
    0.51
    ConstraintMaker
    0.50
    adaptiveStyles
    0.48
    tifiable
    0.48
     betweenstory
    0.46
     ryan
    0.45
     epics
    0.43
    Activations Density 0.275%

    No Known Activations