INDEX

Explanations

abbreviations (possibly medical or scientific) and related terms.

oai_token-act-pair · gemini-2.0-flash

french "r" words

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

-0.67

 LoggerFactory

-0.57

SR

-0.57

sr

-0.57

lgari

-0.56

 Gerr

-0.56

LR

-0.55

MR

-0.55

GR

-0.54

dra

-0.53

POSITIVE LOGITS

 réaction

0.59

 relais

0.58

 relações

0.57

 russes

0.56

 recours

0.56

 ruines

0.56

 raça

0.55

 restantes

0.55

 recessive

0.54

 residence

0.54

Activations Density 2.768%

abbreviations (possibly medical or scientific) and related terms.

french "r" words

No Comments

No Known Activations