© 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. 12237
    Prev
    Next
    INDEX
    Explanations

    german words commonly used in research context

    oai_token-act-pair · gemini-2.0-flash

    Not English

    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
     propOrder
    -0.64
    igy
    -0.59
    hasMoreElements
    -0.58
    tisgarh
    -0.57
    vica
    -0.57
    ganu
    -0.56
    тельстве
    -0.56
    )++;
    -0.55
     BoxFit
    -0.55
    chläge
    -0.54
    POSITIVE LOGITS
     présidenti
    0.56
    Portale
    0.50
     législ
    0.49
     VizieR
    0.45
    GenerationType
    0.45
     casco
    0.44
    ministrazione
    0.42
    Véxase
    0.42
    $_['
    0.42
     transfieras
    0.41
    Activations Density 0.333%

    No Known Activations