INDEX

Explanations

capitalized acronyms and initialisms enclosed in parentheses

oai_token-act-pair · gemini-2.0-flash

(

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

-0.59

-0.47

has

-0.39

enumii

-0.39

can

-0.38

to

-0.36

api

-0.36

جغرافيا

-0.35

POSITIVE LOGITS

 Monfieur

1.07

 houſe

1.04

 Houſe

0.95

 purpoſe

0.95

 myſelf

0.94

Efq

0.91

 Anſ

0.89

 pleaſure

0.89

ſelves

0.88

 ſever

0.88

Activations Density 1.795%

capitalized acronyms and initialisms enclosed in parentheses

(

No Comments

No Known Activations