© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 227
    Prev
    Next
    INDEX
    Explanations

    proper and place names in various languages

    oai_token-act-pair · gemini-2.0-flash

    misspelled words

    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
    stdc
    -0.80
    archiviato
    -0.79
    ذ
    -0.72
    AnchorStyles
    -0.71
    uc
    -0.69
    jstor
    -0.69
    #+#
    -0.69
    cu
    -0.69
    ec
    -0.68
    vor
    -0.67
    POSITIVE LOGITS
    olesale
    0.65
    hematical
    0.52
    encils
    0.51
     سكانية
    0.48
    unately
    0.46
     Efq
    0.44
    ebaran
    0.44
     Româ
    0.43
    höhung
    0.43
     professionali
    0.43
    Activations Density 16.891%

    No Known Activations