© 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. 3915
    Prev
    Next
    INDEX
    Explanations

    text about laws, audits and fines

    oai_token-act-pair · gemini-2.0-flash

    Legal and business penalties

    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
     offense
    -1.37
     offence
    -1.34
     penalty
    -1.32
     Penalty
    -1.27
     penalties
    -1.23
     offenses
    -1.20
     Penalties
    -1.20
     punishment
    -1.20
    pun
    -1.18
     violation
    -1.16
    POSITIVE LOGITS
    ători
    0.56
    CompilerServices
    0.54
     indisponible
    0.51
    SourceChecksum
    0.51
    complexContent
    0.49
     _$
    0.47
    UnknownFieldSet
    0.47
     rhestr
    0.46
    webElementXpaths
    0.46
     Commencez
    0.46
    Activations Density 2.463%

    No Known Activations