INDEX

Explanations

snippets from multiple conversational language with references to code/language/communication, and multiple languages

oai_token-act-pair · gemini-2.0-flash

Non-English language

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 nakalista

-0.96

 resourceCulture

-0.91

 Signalez

-0.87

MessageTagHelper

-0.87

 متعلقه

-0.84

 morrow

-0.79

 purpoſe

-0.78

saraba

-0.78

 throats

-0.76

octanol

-0.76

POSITIVE LOGITS

+};

0.40

 مقاط

0.36

0.34

 szer

0.33

SupportActionBar

0.33

met

0.32

buje

0.32

op

0.32

おく

0.32

 meeting

0.32

Activations Density 0.986%

snippets from multiple conversational language with references to code/language/communication, and multiple languages

Non-English language

No Comments

No Known Activations