INDEX

Explanations

code snippets

oai_token-act-pair · gemini-2.0-flash

Computer Code or other languages

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

TintMode

-0.47

 body

-0.46

 '/':

-0.43

 đối

-0.43

ViewGroup

-0.43

messageInfo

-0.42

zá

-0.41

áját

-0.41

 tissue

-0.41

sei

-0.40

POSITIVE LOGITS

脚注の使い方

0.73

RegressionTest

0.63

__(/*!

0.62

ErrUnexpectedEOF

0.59

bootstrapcdn

0.59

PyExc

0.56

ieno

0.56

 HasFactory

0.55

mybatisplus

0.55

SequentialGroup

0.54

Activations Density 0.367%

code snippets

Computer Code or other languages

No Comments

No Known Activations