© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8085
    Prev
    Next
    INDEX
    Explanations

    the prefix "anti-"

    oai_token-act-pair · gemini-2.0-flash

    anti

    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
    WithIOException
    -0.63
     disambiguazione
    -0.61
     utafitiHapana
    -0.59
    IntoConstraints
    -0.52
     doInBackground
    -0.51
    tvguidetime
    -0.50
    ImageContext
    -0.50
    ieb
    -0.49
     pinulongan
    -0.47
    tagHelperRunner
    -0.46
    POSITIVE LOGITS
     дописавши
    0.60
     endfor
    0.57
     defStyleAttr
    0.54
    RegisterType
    0.53
    mafia
    0.52
     fascic
    0.51
    meris
    0.51
    Semitic
    0.50
    biome
    0.49
     Entom
    0.49
    Activations Density 6.145%

    No Known Activations