INDEX

Explanations

positive words related to product marketing

oai_token-act-pair · gemini-2.0-flash

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

@"/

-0.71

OrNil

-0.69

ArrowToggle

-0.66

bootstrapcdn

-0.64

Архівовано

-0.63

NameInMap

-0.63

SequentialGroup

-0.61

ⓧ

-0.61

GraphicsUnit

-0.59

fortawesome

-0.59

POSITIVE LOGITS

 Osiris

0.50

TF

0.48

tsk

0.47

 skulls

0.46

 buttercream

0.44

criture

0.43

 CURIAM

0.43

Skocz

0.42

;-;

0.42

tf

0.42

Activations Density 6.905%

positive words related to product marketing

more

No Comments

No Known Activations