INDEX

Explanations

LaTeX math symbols

oai_token-act-pair · gemini-2.0-flash

math formulas and symbols

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

FTFY

-0.70

ükemmel

-0.69

ziasztok

-0.69

$_"

-0.68

antenimiento

-0.66

 doubtnut

-0.66

aaral

-0.63

 myſelf

-0.63

pozdrawiam

-0.62

intenance

-0.59

POSITIVE LOGITS

lceil

0.66

lfloor

0.63

langle

0.56

rceil

0.55

{|

0.54

 noDo

0.54

matchCondition

0.53

windowFixed

0.53

ul

0.52

HasKey

0.50

Activations Density 3.591%

LaTeX math symbols

math formulas and symbols

No Comments

No Known Activations