© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 521
    Prev
    Next
    INDEX
    Explanations

    latex math and also finds the possessive form for actors

    oai_token-act-pair · gemini-2.0-flash

    math equations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    Ещё
    -2.66
    Colour
    -2.39
    labour
    -2.38
     colours
    -2.34
     tumour
    -2.33
     utilisation
    -2.33
     tumours
    -2.33
     generalised
    -2.33
     colour
    -2.33
    colour
    -2.33
    POSITIVE LOGITS
    </h1>
    0.48
    </sub>
    0.46
    ьез
    0.41
    ोड़
    0.38
    rieux
    0.38
     būt
    0.38
    stücks
    0.36
     médicament
    0.35
    utscher
    0.35
    šanai
    0.35
    Activations Density 7.243%

    No Known Activations