© 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. 5593
    Prev
    Next
    INDEX
    Explanations

    section headers and reference mentions

    oai_token-act-pair · gemini-2.0-flash

    words or phrases in various languages

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

    references

    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
    ?).
    -0.64
     series
    -0.59
    ?}
    -0.59
    ?”.
    -0.59
     Réponses
    -0.57
    ?),
    -0.56
    ?)
    -0.56
    #+#
    -0.55
     R
    -0.54
    ?</
    -0.53
    POSITIVE LOGITS
    حياته
    0.72
     démocr
    0.70
     étoient
    0.65
     correctes
    0.63
     avoient
    0.63
     eorum
    0.61
     quæ
    0.60
     igång
    0.59
     noastră
    0.59
     anún
    0.59
    Activations Density 4.474%

    No Known Activations