© 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. 685
    Prev
    Next
    INDEX
    Explanations

    Spanish language articles

    oai_token-act-pair · gemini-2.0-flash

    de

    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
     sin
    -0.53
    sin
    -0.50
    Geplaatst
    -0.45
     el
    -0.45
     a
    -0.44
     sina
    -0.44
    ChildScrollView
    -0.43
    richTextPanel
    -0.43
    HttpFoundation
    -0.42
    ël
    -0.42
    POSITIVE LOGITS
     تانيه
    0.79
     pleaſure
    0.75
     Majefty
    0.61
    cluye
    0.59
     كومونز
    0.58
    ſelves
    0.58
     Jefus
    0.58
     purpoſe
    0.58
     itſelf
    0.57
    OOTDTY
    0.57
    Activations Density 1.196%

    No Known Activations