INDEX

Explanations

technical terms, whether related to scientific research, product development, community engagement or emotional impact.

oai_token-act-pair · gemini-2.0-flash

system implementation/development

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

Efq

-1.02

 pleaſure

-0.91

 myſelf

-0.89

 Monfieur

-0.84

 houſe

-0.76

 ſhe

-0.74

 iſt

-0.74

ſelf

-0.74

Eſ

-0.73

 purpoſe

-0.73

POSITIVE LOGITS

 通販

0.58

ddots

0.53

de

0.45

en

0.43

Müller

0.42

Wrath

0.42

ga

0.42

TabIndex

0.41

vo

0.41

kehrt

0.40

Activations Density 10.330%

technical terms, whether related to scientific research, product development, community engagement or emotional impact.

system implementation/development

No Comments

No Known Activations

technical terms, whether related to scientific research, product development, community engagement or emotional impact.

system implementation/development

No Comments

No Known Activations