INDEX

Explanations

the letter "z" and question marks in equations or mathematical expressions.

oai_token-act-pair · gemini-2.0-flash

z

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

the

-0.78

-0.69

it

-0.68

 that

-0.63

his

-0.63

 significant

-0.60

us

-0.59

off

-0.57

our

-0.57

POSITIVE LOGITS

 NSCoder

0.93

 MainAxisSize

0.89

ZF

0.88

 Shaksp

0.82

argout

0.81

Efq

0.81

 starlight

0.80

 Zaire

0.79

 <>",

0.79

ZS

0.79

Activations Density 0.557%

the letter "z" and question marks in equations or mathematical expressions.

z

No Comments

No Known Activations