© 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. 14672
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to negative consequences

    oai_token-act-pair · gemini-2.0-flash

    variations of "toward"

    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
     Damage
    -1.58
    Damage
    -1.52
     harm
    -1.48
     damage
    -1.45
    damage
    -1.41
     hurt
    -1.39
     harmed
    -1.37
    DAMAGE
    -1.32
     DAMAGE
    -1.31
     Harm
    -1.29
    POSITIVE LOGITS
     toward
    2.06
    toward
    2.00
     Toward
    1.78
    Toward
    1.68
    towards
    1.58
     Towards
    1.52
    Towards
    1.52
     towards
    1.52
     hacia
    1.16
     verso
    1.05
    Activations Density 1.707%

    No Known Activations