© 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. 4443
    Prev
    Next
    INDEX
    Explanations

    negative statements about authority, control, or police

    oai_token-act-pair · gemini-2.0-flash

    official and legal statements

    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
    Билгалдахарш
    -0.61
     AssemblyCulture
    -0.55
    &$
    -0.54
    enumii
    -0.53
    phosa
    -0.52
     Rosas
    -0.50
     }?>
    -0.49
    ")))
    -0.49
    ++
    -0.49
    SGS
    -0.49
    POSITIVE LOGITS
     typelib
    0.61
    PropertyGroup
    0.55
    EndContext
    0.55
    StoryboardSegue
    0.54
     ***!
    0.52
    mişti
    0.50
    BufferException
    0.50
    Affiliation
    0.50
    Extinguishing
    0.50
     Amounts
    0.49
    Activations Density 2.866%

    No Known Activations