INDEX

Explanations

question/answer forum posts seeking help. It especially emphasizes things like names, dating and possible donations

oai_token-act-pair · gemini-2.0-flash

advertisements and snippets

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

InitVars

-0.92

 resourceCulture

-0.82

 ProtoMessage

-0.76

InSection

-0.66

@"/

-0.64

TagMode

-0.63

PerformLayout

-0.61

Distribuzione

-0.60

SuspendLayout

-0.58

Ecotoxicity

-0.58

POSITIVE LOGITS

 aikaa

0.50

pcm

0.47

BBA

0.47

 corals

0.47

 bave

0.46

出版年

0.46

 Andra

0.45

 ilman

0.45

srs

0.45

 Sanskrit

0.44

Activations Density 9.384%

question/answer forum posts seeking help. It especially emphasizes things like names, dating and possible donations

advertisements and snippets

No Comments

No Known Activations