INDEX

Explanations

code snippets including numbers, underscores, equals signs and letters like F, B.

oai_token-act-pair · gemini-2.0-flash

Separators

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

-0.62

Lähteet

-0.60

-0.54

Jegyzetek

-0.54

Fordítás

-0.50

-0.49

-0.47

hsl

-0.46

 ioutil

-0.44

bet

-0.44

POSITIVE LOGITS

BeginInit

0.71

DoubleQuotes

0.70

 насељу

0.61

 itſelf

0.60

 Audiodateien

0.58

 tranſ

0.57

SharedCtor

0.57

 poffe

0.56

 Normdatei

0.56

 незавершена

0.56

Activations Density 8.114%

code snippets including numbers, underscores, equals signs and letters like F, B.

Separators

No Comments

No Known Activations