© 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. 14910
    Prev
    Next
    INDEX
    Explanations

    a mix of coding symbols, foreign languages, and possible citations, with a high emphasis on low ASCII values.

    oai_token-act-pair · gemini-2.0-flash

    Foreign 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
     Sodom
    -0.15
     Berber
    -0.14
     Mongolian
    -0.14
     steppe
    -0.14
     Pythagoras
    -0.14
     Khmer
    -0.14
     albumin
    -0.14
     InputDecoration
    -0.14
     hammer
    -0.14
     Eiffel
    -0.13
    POSITIVE LOGITS
     parachoque
    0.43
     varandra
    0.42
     anún
    0.41
     engraçadas
    0.40
     desmotivaciones
    0.40
     feltro
    0.39
    praš
    0.39
     kepad
    0.39
     kabát
    0.39
     indígen
    0.38
    Activations Density 7.486%

    No Known Activations