INDEX

Explanations

statements of personal opinion or questions about a state of affairs

oai_token-act-pair · gemini-2.0-flash

modal verbs

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 ujednoznacz

-0.66

 ब्रेकडाउन

-0.63

 <>",

-0.63

parsedMessage

-0.62

là

-0.60

Numerology

-0.59

ngrx

-0.59

 appartiennent

-0.59

unknownFields

-0.59

 Référence

-0.58

POSITIVE LOGITS

 will

0.76

 should

0.67

 could

0.61

"}")

0.61

 SHOULD

0.58

 <<<<<<<<<<<<<<

0.58

"}";

0.56

 θα

0.55

 devrait

0.55

 должна

0.54

Activations Density 2.098%

statements of personal opinion or questions about a state of affairs

modal verbs

No Known Activations