INDEX

Explanations

words which are verbs, including both base forms and conjugated forms

oai_token-act-pair · gemini-2.0-flash

trigger

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 triggered

-0.77

triggered

-0.74

Triggered

-0.72

 triggering

-0.65

 activated

-0.63

 triggers

-0.60

 trigger

-0.59

trigger

-0.59

 stimulating

-0.57

 initiated

-0.57

POSITIVE LOGITS

 Мексичка

0.79

ſelves

0.78

ſelf

0.69

 ddelweddau

0.68

 Jefus

0.66

IntoConstraints

0.66

 numberOfRows

0.66

Hochspringen

0.65

 useStyles

0.65

 iprot

0.65

Activations Density 9.407%

words which are verbs, including both base forms and conjugated forms

trigger

No Comments

No Known Activations