INDEX

Explanations

the keyword 'return' and related punctuation like parenthesis and semi-colons

oai_token-act-pair · gemini-2.0-flash

return

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

Not in Any Lists

No Comments

Negative Logits

-0.48

go

-0.44

Pal

-0.43

]={

-0.42

ibel

-0.42

 تول

-0.41

zegor

-0.41

pe

-0.41

ору

-0.41

POSITIVE LOGITS

 Theſe

0.82

 itſelf

0.76

Efq

0.76

 GenerationType

0.75

 BoxFit

0.71

 Jefus

0.70

 HasFactory

0.70

 Shakspeare

0.69

 photolibrary

0.68

 Monfieur

0.68

Activations Density 0.787%

the keyword 'return' and related punctuation like parenthesis and semi-colons

return

No Comments

No Known Activations