© 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. 698
    Prev
    Next
    INDEX
    Explanations

    hyphens in text

    oai_token-act-pair · gemini-2.0-flash

    dash

    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
     Roskov
    -0.71
    ſelves
    -0.71
    verwijspagina
    -0.69
    modb
    -0.68
     quæ
    -0.67
    étape
    -0.66
    boats
    -0.66
     stället
    -0.65
    extrémité
    -0.63
    piram
    -0.63
    POSITIVE LOGITS
    s
    0.44
     intptr
    0.42
     anda
    0.42
     reg
    0.41
    hängt
    0.40
     dAtA
    0.38
     ya
    0.37
     op
    0.37
    griffen
    0.36
    与
    0.36
    Activations Density 5.689%

    No Known Activations