INDEX

Explanations

code snippets

oai_token-act-pair · gemini-2.0-flash

image processing

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

iläum

-0.44

Base

-0.43

 base

-0.42

dane

-0.41

zo

-0.41

 probe

-0.39

 insuffisamment

-0.39

 Base

-0.38

dro

-0.38

Editors

-0.38

POSITIVE LOGITS

 <<<<<<<<<<<<<<

0.79

 transfieras

0.77

 utafitiHapana

0.75

 disambiguazione

0.72

 تانيه

0.71

hasMoreElements

0.71

 nakalista

0.69

Geplaatst

0.68

Tikang

0.68

 للاسماء

0.67

Activations Density 0.393%

code snippets

image processing

No Known Activations