INDEX

Explanations

numbers followed by a period

oai_token-act-pair · gemini-2.0-flash

arXiv papers

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

Not in Any Lists

No Comments

Negative Logits

coltà

-0.48

 typelib

-0.47

Portale

-0.47

ỏi

-0.45

idom

-0.45

jiny

-0.45

ijn

-0.44

achal

-0.44

mut

-0.44

 BoxDecoration

-0.43

POSITIVE LOGITS

 désolés

0.70

GOTREF

0.65

 noDo

0.64

ThroughAttribute

0.63

 ſtate

0.62

InstrumentedTest

0.59

 تكبرها

0.58

richTextPanel

0.57

tersebut

0.56

Carcinogenicity

0.55

Activations Density 2.076%

numbers followed by a period

arXiv papers

No Comments

No Known Activations