© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6299
    Prev
    Next
    INDEX
    Explanations

    the letters "Ne" or "ne"

    oai_token-act-pair · gemini-2.0-flash

    Ne

    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
    AnimationsModule
    -0.59
    Izvori
    -0.52
    ArgsConstructor
    -0.51
    ambilan
    -0.48
    FunctionFlags
    -0.47
     consultato
    -0.47
    లాలు
    -0.47
     Administrativna
    -0.45
    niająca
    -0.45
    AndEndTag
    -0.44
    POSITIVE LOGITS
    adaptiveStyles
    0.61
    ktop
    0.53
    RTRS
    0.53
    pubmed
    0.53
    ospor
    0.52
    omorphic
    0.52
    nocache
    0.50
    omorph
    0.49
    obar
    0.49
    pture
    0.49
    Activations Density 3.702%

    No Known Activations