INDEX

Explanations

geographic terms, especially related to the location of forest fires

oai_token-act-pair · gemini-2.0-flash

News and locations

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

migrationBuilder

-0.82

GEBURTSDATUM

-0.79

iastes

-0.79

addCriterion

-0.75

 كومونز

-0.70

ViewFeatures

-0.70

ніципалі

-0.70

endphp

-0.70

tagHelperRunner

-0.69

mybatisplus

-0.69

POSITIVE LOGITS

Sub

0.40

ser

0.37

Ban

0.37

 Werner

0.36

Lar

0.36

Mod

0.36

Sh

0.35

UseVisualStyle

0.35

 Inter

0.35

sub

0.35

Activations Density 2.957%

geographic terms, especially related to the location of forest fires

News and locations

No Comments

No Known Activations