INDEX

Explanations

a variety of words from what appears to be different non-English languages, or possibly words with unicode characters

oai_token-act-pair · gemini-2.0-flash

Foreign language/code snippets

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

 незавершена

-0.92

 CreateTagHelper

-0.92

expandindo

-0.90

Hauptartikel

-0.87

bewerken

-0.85

 unknownFields

-0.83

Sucesor

-0.81

 <=",

-0.81

̍t

-0.79

 متعلقه

-0.79

POSITIVE LOGITS

0.48

‘

0.45

0.44

Die

0.44

↵↵

0.43

section

0.43

Activations Density 12.317%

a variety of words from what appears to be different non-English languages, or possibly words with unicode characters

Foreign language/code snippets

No Comments

No Known Activations